AI/Agent Engineer

About the Role vega is looking for an AI/Agent Engineer in London. This position focuses on designing and building intelligent agents that address complex challenges. Work will directly support the advancement of AI solutions across the company.

Join Our Innovative Team as a Senior AI Engineer (Agentic Systems)At StarCompliance, we are at the forefront of creating software solutions that address critical compliance needs for our global clientele. As we integrate AI as a fundamental capability throughout our software development lifecycle, we invite you to be part of this transformative journey.We are looking for a Senior AI Engineer to spearhead the practical implementation and expansion of AI-assisted and agentic engineering within our teams. This is a hands-on role where you will engage directly with real codebases, leveraging cutting-edge AI-native development environments (Cursor preferred) to revolutionize the software development process.Your mission will be to evolve AI from a mere tool into a fully embedded system that is repeatable and scalable. You will craft and execute playbooks, establish workflows, and define patterns that allow our teams to harness the power of parallel AI agents, facilitate autonomous code reviews, and create AI-driven delivery pipelines. Additionally, you will play a pivotal role in launching new initiatives, ensuring they are built on the right architecture and AI-enabled engineering practices from the outset.This position is part of our R&D Engineering team and collaborates closely with Platform, QA, and Product Engineering. Here, influence is gained through tangible delivery rather than hierarchy.Our Vision of AIWe view AI not just as an assistant, but as an integral component of our engineering ecosystem. We expect engineers in this role to embrace this perspective and drive our AI initiatives forward.

Role overview ServiceNow is seeking a Senior AI Agent Engineer to join the Customer Deployment team in London. The position centers on building and deploying advanced AI agent solutions that support clients in meeting their objectives. Deep experience in artificial intelligence and engineering is essential, especially in the context of customer deployment strategies. What you will do Design, develop, and maintain AI agent systems tailored to customer requirements Collaborate with cross-functional teams to ensure effective implementation of AI solutions Refine and enhance AI capabilities to improve user experience and drive customer satisfaction Collaboration and impact This position sits at the intersection of engineering and customer success. The Senior AI Agent Engineer will work with teams across ServiceNow, helping deliver reliable and effective AI deployments that create tangible value for clients.

Join Our Team as a Senior Data Scientist - Conversational & Agentic AILocation: London (Hybrid)About SwapAt Swap, we are at the forefront of revolutionizing agentic commerce with our innovative AI-native platform. We connect backend operations seamlessly with a modern storefront experience.Our platform is tailored for brands eager to expand their reach, enabling them to sell anything, anywhere. Swap consolidates global operations, enhances intelligent workflows, and empowers businesses to make informed decisions with real-time data. Our extensive product range includes solutions for cross-border transactions, tax management, returns, demand planning, and next-generation agentic storefronts, providing merchants with full transparency and confidence in their operations.We foster a company culture that values clarity, creativity, and shared ownership as we redefine the landscape of global commerce.About the RoleWe are looking for a Senior Data Scientist to spearhead the development and evaluation of intelligent autonomous AI agents focused on B2B analytics and operational workflows. You will be responsible for engineering sophisticated systems that enable agents to autonomously analyze data, generate actionable insights, execute operational tasks, and orchestrate complex business processes. Your role will involve working across analytical and operational workflows, designing multi-agent ecosystems, establishing evaluation frameworks, and ensuring the reliability of complex agentic systems in production.Key ResponsibilitiesAgentic System Design & Multi-Agent Architecture: Architect AI agent ecosystems capable of autonomously managing analytical and operational workflows, including data exploration, insight generation, process automation, and cross-functional coordination.Analytical & Operational Workflow Design: Create agent systems that proficiently navigate data discovery, hypothesis testing, insight delivery, and operational task execution, effectively managing transitions between specialized agents (SQL, visualization, statistical analysis, workflow automation).Prompt Engineering & Agent Optimization: Craft and refine prompts for autonomous agents, incorporating few-shot learning, chain-of-thought reasoning, tool usage, and structured output generation for multi-step analytical and operational workflows.Comprehensive Evaluation Frameworks: Develop evaluation systems that measure analytical accuracy, operational task success, agent reliability, and coordination effectiveness. Create automated testing suites, benchmark datasets, and continuous production monitoring protocols.Agent Performance Analysis: Conduct thorough analyses of agent performance to drive system improvements and enhance operational efficiency.

About UsAt Sierra, we are revolutionizing the way businesses engage with their customers through innovative AI solutions. Our mission is to craft exceptional, human-centric customer experiences. With our headquarters in San Francisco and expanding offices in London, Atlanta, New York, France, Singapore, and Japan, we are at the forefront of technology.Our corporate culture is deeply rooted in our core values: Trust, Customer Obsession, Craftsmanship, Intensity, and Family. These principles guide our actions and decisions, shaping a collaborative and empowering work environment.Led by co-founders Bret Taylor and Clay Bavor, Sierra is positioned for growth. Bret has an impressive background, having served as co-CEO of Salesforce and CTO of Facebook, while Clay has dedicated years at Google leading groundbreaking projects in AR/VR and product design.Your RoleArchitect and deploy state-of-the-art AI agents: You will be responsible for designing, developing, and launching high-performance AI agents that are pivotal to Sierra’s success, enhancing customer interactions across various sectors such as finance, healthcare, and e-commerce.Lead the Agent Development Life Cycle: Take full ownership of projects from inception to deployment and sustained enhancements, establishing best practices and ensuring the highest standards are met in AI development.Collaborate with industry leaders: Engage directly with top executives at major enterprises and dynamic startups, identifying their challenges and pioneering AI solutions that drive operational transformation.

Ebury empowers ambitious businesses to achieve global growth, and we extend the same philosophy to our team members. We champion innovation, collaboration, and problem-solving, creating an inclusive environment where everyone feels valued, supported, and motivated to excel.If you are a collaborative individual eager to revolutionize the way businesses operate globally, reach out to us — we would love to explore how Ebury can expedite your career progression and enable you to shape the future.Senior Full-Stack Engineer - AI Agent PlatformLocation: London Victoria Office - Hybrid: 4 days in the office, 1 day working from homeAbout the RoleWe are developing an AI-driven financial crime investigation platform that is transforming the operational efficiency of Ebury's compliance teams. Our AI agents are designed to manage thousands of screening cases, alleviating the workload of analysts while ensuring compliance with regulatory standards.We seek a Senior Full-Stack Engineer to enhance our platform and elevate our engineering standards. You will design and implement complex features across the entire stack—from React frontends to Python backends and LLM integrations—while mentoring colleagues and influencing our technical strategy.This is an exceptional opportunity to work at the crossroads of AI/ML, fintech, and compliance, developing production-grade AI systems that tackle real financial crime investigations at scale.What You Will DoArchitect and construct end-to-end features across our React frontend and FastAPI backend...

About DecagonDecagon stands at the forefront of conversational AI, empowering brands to deliver exceptional concierge-level customer experiences. Our innovative technology enables prominent enterprises such as Avis Budget Group, Block’s Cash App and Square, Chime, Oura Health, and Hunter Douglas to deploy intelligent AI agents that facilitate personalized and engaging interactions across various channels, including voice, chat, email, and SMS.We are crafting a future where customer interactions are transformed from mere support tickets and hold music into swift resolutions and rich conversations, fostering deeper relationships. Supported by leading investors such as a16z, Accel, Bain Capital Ventures, Coatue, and Index Ventures, we are committed to this vision.As an in-office company, we thrive on a culture of excellence and speed, guided by our core values: Just Get It Done, Invent What Customers Want, Winner’s Mindset, and The Polymath Principle.About the TeamThe Agent Software Engineering team at Decagon is dedicated to deploying cutting-edge conversational AI agents that impact millions of users and drive our growth. You will lead a team in enhancing our industry-leading AI platform, collaborating closely with customers and leveraging your creativity to develop scalable solutions that meet their evolving needs.Our mission is to create enchanting support experiences where AI agents work in tandem with human agents to resolve user issues effectively.About the RoleAs we expand with a new office in London, Decagon is seeking an Engineering Manager to establish and cultivate its culture from the ground up. In this pivotal role, you will have full ownership and autonomy in delivering top-tier AI agents, overseeing everything from initial implementation to ongoing refinement. You will engage directly with leaders across diverse sectors such as finance, healthcare, and hospitality, addressing their users’ needs with reliable and intuitive AI solutions.Our engineers take pride in owning their projects from start to finish and are empowered to make a significant impact. This position is ideal for someone eager to mentor junior engineers, tackle complex system challenges, and craft elegant, scalable solutions for millions of users.

Join Nebius and Shape the Future of AINebius is pioneering a transformative approach to cloud computing, dedicated to empowering the global AI economy. Our mission is to provide the essential tools and resources that enable our clients to tackle real-world challenges and revolutionize industries, all while minimizing infrastructure costs and the necessity of extensive in-house AI/ML teams. Our talented workforce operates at the forefront of AI cloud infrastructure, collaborating with some of the most innovative and experienced leaders and engineers in the industry.Our Work EnvironmentLocated in Amsterdam and publicly listed on Nasdaq, Nebius boasts a global presence with R&D centers across Europe, North America, and Israel. Our diverse team, comprising over 1,400 employees, includes more than 400 highly skilled engineers, equipped with deep expertise in both hardware and software engineering, as well as an in-house AI R&D team.We are on the lookout for a Staff or Principal Applied AI Researcher to join our rapidly expanding team, focused on developing an agent-native search platform—the vital web access layer for AI systems.Unlike traditional search methodologies, we are innovating how AI agents—not humans—access, retrieve, and reason over information available on the internet. As AI increasingly becomes the primary interface for web interaction, this pivotal layer is set to transform the function of conventional search engines.This role involves tackling retrieval and search challenges within entirely new access patterns and scales.Depending on your experience and the responsibilities you take on, this position can be classified at either the Staff or Principal level, granting you ownership over vital aspects of our applied AI research trajectory.You will lead applied research initiatives that directly enhance how AI systems retrieve, ground, and utilize real-world information in production, ensuring that research is closely linked to large-scale deployment.Your ResponsibilitiesEngage in projects at the intersection of search, retrieval, and LLM-based systems, shaping how AI agents engage with the web. This includes designing agent-native retrieval systems (distinct from human search UX), developing systems where LLMs actively query, iterate, and reason over results, and collaborating with cross-functional teams to foster innovation.

Join us at Docker, where we revolutionize app development, allowing developers to concentrate on what truly matters. Our remote-first global team thrives on innovation and enhancing the developer experience. With over 20 million monthly users and 20 billion image pulls, Docker stands as the premier tool for building, sharing, and running applications—trusted by both startups and Fortune 100 companies. As we rapidly expand, we're just getting started. Come aboard and enjoy this exciting journey!We are seeking a Principal Software Engineer (Docker Agents) to join our AI engineering team to shape the future of containerized AI agents. Docker containers provide the ideal environment for hosting and executing AI agents, ensuring isolation, portability, and reproducibility. You will work on our open-source project, cagent (https://github.com/docker/cagent), and enhance it to empower developers in building, deploying, and scaling intelligent agents utilizing Docker’s container technology.This is a unique opportunity to influence how developers harness containers for AI agents on a large scale. You will establish the technical vision, spearhead architectural decisions, and collaborate with engineers and leaders across Docker to integrate containerized agent capabilities into the developer experience.

Join Endava as a Solution Developer, specializing in Agentic AI. This entry-level position presents a unique opportunity for recent graduates and aspiring developers to work in a dynamic client delivery environment. You will be involved in innovative projects that challenge your programming skills and creativity, while collaborating with industry experts.

At Docker, we are dedicated to simplifying application development, allowing developers to concentrate on what truly matters. Our remote-first team is global, united by a shared passion for innovation and exceptional developer experiences. With over 20 million monthly users and 20 billion image pulls, Docker stands as the leading tool for building, sharing, and running applications, trusted by both startups and Fortune 100 companies alike. We are in a rapid growth phase and just getting started. Join us for an exciting journey!As part of Docker's AI engineering team, you will play a pivotal role in shaping the future of containerized AI agents. Docker containers serve as the ideal platform to host and execute AI agents, providing isolation, portability, and reproducibility.You will contribute to Docker Agent, our open-source project (https://github.com/docker/docker-agent), enhancing it to empower developers to build, deploy, and scale intelligent agents using Docker's container technology.This position offers a unique greenfield opportunity to influence how developers utilize containers for AI agents at scale. You will collaborate with a team of experienced engineers and work closely with our sister teams focused on Ask Gordon and Docker's broader AI platform. This role combines cutting-edge AI techniques with container technology to address real-world developer challenges.Important Note: This position is only available to candidates currently residing in London (or within a reasonable commuting distance). We cannot make exceptions to this location requirement.

At Swap, we are revolutionizing the landscape of modern agentic commerce through our innovative AI-native platform. Our technology seamlessly integrates backend operations with an advanced storefront experience, empowering brands to sell anything, anywhere.Designed for forward-thinking brands, Swap centralizes global operations, enhances intelligent workflows, and enables margin-protecting decisions utilizing real-time data. Our comprehensive product suite encompasses cross-border logistics, tax management, returns processing, demand planning, and our pioneering agentic storefront, ensuring merchants have full transparency and the confidence to act decisively.We are committed to fostering a culture that prioritizes clarity, creativity, and shared ownership as we redefine the dynamics of global commerce.About the RoleWe are seeking an extraordinary individual who transcends traditional data science. Our ideal candidate embodies: • A blend of human intuition and machine intelligence. • The ability to run parallel code paths and deploy agents to explore solutions autonomously.Join our Agentic squad, collaborating with five other AI and data science experts to refine, scale, and innovate the intelligence layer that powers our agentic storefront. This senior-level, high-agency generalist role is for someone who can navigate models, agents, experiments, and product decisions with agility and speed in a startup setting.Key ResponsibilitiesWork in tandem with Product, Engineering, and the Agentic team to enhance AI-driven features throughout the entire commerce journey.Design and refine recommendation and personalization systems leveraging behavioral and transactional data.Advance conversational agents, multi-agent workflows, and tool integrations.Iterate on virtual try-on and vision systems using prompt engineering, fine-tuning, and model chaining.Rapidly prototype new AI functionalities and transition them into production-grade systems.Establish and enhance experimentation frameworks, including A/B testing, evaluation pipelines, and benchmarking.Drive improvements in conversion, retention, and operational efficiency through applied machine learning.Identify automation opportunities and design agent-driven internal tools.

Role Overview The Trade Desk is hiring a Staff Software Engineer to help build advanced AI solutions. This London-based role centers on designing and implementing software systems that support and improve AI-driven products. What You Will Do Design and implement software systems for AI applications Work closely with teams across disciplines to expand product capabilities Support integration of new technologies into existing products Collaboration This role involves frequent collaboration with cross-functional teams to ensure AI systems are effective and integrate smoothly with other offerings.

About Checkout.com Checkout.com powers digital payments for well-known brands such as eBay, ASOS, Klarna, Uber Eats, and Sony. Our technology supports billions of online transactions each year, helping businesses deliver smooth checkout experiences that drive growth and customer loyalty. With a presence in 19 offices across six continents and headquarters in London, our team brings together a global perspective. Every role here offers a chance to shape the future of fintech alongside colleagues committed to high standards and ongoing improvement. Role Overview: Manager, Product Marketing for AI and Agentic Commerce The Manager, Product Marketing for AI and Agentic Commerce will guide product marketing strategies at Checkout.com. This role works closely with Product, Commercial, and Marketing teams to deliver go-to-market plans and shape how we communicate our leadership in this evolving space. Expect to work hands-on with new technologies and trends, producing product marketing outcomes that support a range of initiatives. Key Responsibilities Lead product marketing for AI and agentic commerce, turning complex features into clear, engaging stories. Own go-to-market strategies: manage product launches, marketing campaigns, and content development, ensuring delivery meets business goals and timelines. Shape category positioning by defining and strengthening Checkout.com’s presence in agentic commerce and AI. Location This position is based in London.

Why Join NebiusNebius is at the forefront of a transformative era in cloud computing, dedicated to empowering the global AI economy. We develop innovative tools and resources that enable our customers to tackle real-world challenges and revolutionize industries, all while minimizing infrastructure expenses and eliminating the need for extensive in-house AI/ML teams. Our workforce operates at the cutting edge of AI cloud infrastructure, collaborating with some of the most skilled and visionary leaders and engineers in the domain.Our Work EnvironmentWith our headquarters in Amsterdam and publicly listed on Nasdaq, Nebius boasts a global presence with R&D facilities across Europe, North America, and Israel. Our diverse team of over 1,400 professionals includes more than 400 highly qualified engineers with profound expertise in both hardware and software engineering, complemented by an in-house AI R&D team. The ProductIn today’s fast-paced world, confidence in AI systems relies on AI agents being anchored in accurate, up-to-date real-world information. Search functionality is essential to achieve this.We are developing an agent-centric search platform tailored specifically for AI systems, rather than traditional human users. Our product offers programmatic, low-latency, and observable search APIs that AI agents utilize to access, filter, and reason over real-world data at scale.The RoleWe are seeking a Senior Software Engineer to contribute to the runtime systems of our innovative search engine designed for agentic AI applications.In this capacity, you will be responsible for developing low-latency, high-throughput systems that deliver search results in real-time. Your work will be pivotal in managing user-facing requests, where factors like performance, predictability, and efficiency directly influence product excellence. You will architect and manage systems capable of processing thousands of requests per second while adhering to strict latency requirements, optimizing every aspect from request handling to data retrieval and response generation.

About UsAt Sierra, we're on a mission to revolutionize customer experiences through our innovative AI platform. With headquarters in San Francisco and expanding offices in cities like London, New York, and Singapore, we are dedicated to creating meaningful interactions between businesses and their customers.Our core values—Trust, Customer Obsession, Craftsmanship, Intensity, and Family—define our culture and drive our commitment to excellence in every project we undertake.Our visionary co-founders, Bret Taylor and Clay Bavor, bring a wealth of experience from leading tech giants like Google and Salesforce, ensuring that our team is equipped with unparalleled expertise in the field.Your RoleDesign and deliver robust AI agents: You will create high-performing, reliable, and intuitive AI agents that are crucial to Sierra's growth, operating across diverse sectors such as finance, healthcare, and e-commerce.Lead the Agent Development Life Cycle (ADLC): You will take charge from pilot development through to deployment and ongoing refinement, setting benchmarks for best practices in the industry.Collaborate with industry leaders: By partnering with major enterprises and innovative startups, you will address critical business challenges and integrate AI solutions that transform operational efficiencies.

At Coram AI, we are revolutionizing video security in today's digital landscape. Our innovative cloud-native platform leverages cutting-edge computer vision and artificial intelligence to empower businesses with enhanced safety, informed decision-making, and rapid response capabilities. Experience real-time alerts, effortless clip sharing, and comprehensive visibility across multiple sites.Joining our dynamic, agile team means embracing clarity, excellence, and impactful contributions. Every team member has a voice, delivers significant work, and plays a vital role in shaping how AI can foster a safer and more interconnected world.In this role, you will be part of a pioneering team responsible for managing a sophisticated infrastructure that transcends conventional cloud setups. Beyond our robust AWS and Kubernetes configurations, we also oversee a vast array of IoT devices. We are in search of a skilled engineer who will play a crucial role in developing and maintaining our edge and cloud stack that supports our IoT product offerings, focusing on both infrastructure and the bespoke software we utilize.You will tackle intriguing challenges at the confluence of user experience, machine learning, and infrastructure, while committing to excellence, continuous learning, and delivering exceptional products in a fast-paced startup environment.

Position: Founding Go-to-Market (GTM) Specialist for AI Agents Department: Eliza, Lottie. Reports directly to Chris Hart, GM of Eliza Compensation: OTE £60,000 - £120,000 (Base Salary ranging from £30,000 to £60,000) + Equity Culture & Benefits: Discover more here Equity Offering: Attractive EMI share options Vacation: 26 days plus bank holidays Vision: Transform later life for all and innovate the future of the care sector Work Model: Hybrid, requiring a minimum of 2 office days per week Office Location: London Bridge, London, UK The RoleJoin us in revolutionizing the social care landscape with Eliza, Lottie's cutting-edge AI voice agent. Eliza is designed to manage phone calls for care homes, capture inquiries, book viewings, and ensure every call is addressed. After completing her inaugural shift, we are expanding our reach through our pilot partner network.We are in search of a pioneering GTM professional to launch Eliza into the market. This is an exceptional chance to be the first commercial representative for an innovative AI solution within one of the UK's rapidly expanding startups, supported by Accel and General Catalyst. Collaborate directly with the GM and CEO to construct the go-to-market strategy from the ground up, encompassing the initial outreach to successfully closing deals.If you have thrived as a top-performing SDR or Commercial Associate and aspire to take full ownership of a product's GTM strategy, or if you have experience selling SaaS solutions to small and medium businesses and are ready to embrace a truly innovative AI product, we want to hear from you. We seek a candidate who is entrepreneurial, commercially astute, and eager to introduce transformative solutions to a sector that is in dire need of innovation.As the first in a burgeoning line of AI agent products, this is your opportunity to define the GTM framework that will facilitate expansion across our product portfolio. Key ResponsibilitiesManage the complete sales cycle for Eliza, from prospecting to demonstration and closing deals—targeting care home operators and home care providers.Establish your outbound marketing strategy from the ground up: refine messaging, explore various channels, and utilize Lottie's extensive network of over 6,000 care services for warm introductions.Conduct product demonstrations and represent Eliza at industry events to drive lead generation.Collaborate closely with the Eliza product and engineering teams to relay operator feedback and influence product development.

Join Our Innovative Team at DexAt Dex, we harness the power of AI to revolutionize recruitment by connecting outstanding software engineers with leading tech companies. As one of the fastest-growing startups in the UK, we have secured $3.1 million in funding from prestigious investors such as a16z and Concept Ventures. Our mission is to develop a cutting-edge voice agent, advanced matching engine, and a seamless web application experience that transforms the landscape of talent acquisition.We are looking for a passionate Backend Software Engineer to join our dynamic team. In this role, you will contribute to building our innovative products and AI-driven agent systems, enabling a deeper understanding of our users and their unique opportunities.Your Role and ResponsibilitiesAs a Backend Software Engineer at Dex, you will take ownership of the backend infrastructure that powers our voice agent and other applications. You will be working with a modern tech stack that includes Python, FastAPI, Postgres, Redis, Docker, and Pydantic AI, all hosted on Google Cloud Platform (GCP). Your responsibilities will encompass:Product Backend: Manage critical components of our backend architecture, ensuring new features are implemented securely and are scalable from inception.Agent Backend: Enhance the infrastructure supporting our voice agent, which includes conducting evaluations, improving information extraction methods, and guaranteeing reliable performance at scale.Observability: Implement monitoring, logging, and performance metrics to maintain visibility into our production systems.Matchmaking: Design and optimize the systems that drive our AI-powered talent matching engine.What You Will AchieveArchitect and develop scalable backend systems for AI workflows and product infrastructure.Ensure reliability and performance of the systems supporting our voice agent and web application.Collaborate with team members to set technical direction, architecture, and long-term objectives.Create and maintain robust APIs, authentication frameworks, and database designs.Work closely with product managers, designers, and engineers to build infrastructure that adapts to changing requirements.Contribute to establishing best practices for system reliability, performance, and deployment speed.

About Indicium AI Indicium AI is a premier global consultancy specializing in AI solutions for the world's leading enterprises. With a proven track record across various sectors including Financial Services, Energy & Utilities, Healthcare & Life Sciences, Retail & CPG, and Manufacturing, we provide unmatched clarity, speed, and capability in delivering AI at scale. Our team of over 600 AI experts supports more than 50 enterprise clients from 5 global locations, collaborating with top-tier partners such as Anthropic, Databricks, AWS, OpenAI, and Microsoft to achieve impactful business outcomes. Overview We are looking for a talented AI Engineer to join our team, responsible for designing, building, and deploying robust production-grade AI systems that leverage large language models. This unique position merges software engineering with AI implementation, focusing on developing scalable, reliable applications instead of model training or research. As part of your role, you will utilize cutting-edge LLM technologies to create sophisticated AI systems capable of solving complex real-world challenges through multi-agent orchestration, intelligent tool integration, and efficient production workflows. Your expertise will be pivotal in crafting the orchestration layer that ensures these systems are production-ready, effectively managing failure modes, optimizing agent collaboration, and providing consistent, reliable outputs at scale. You'll blend strong software engineering fundamentals with comprehensive knowledge of LLM capabilities, limitations, and best practices for building trustworthy non-deterministic systems. Responsibilities Design and implement production AI systems that incorporate LLMs, RAG pipelines, vector databases, and agentic frameworks. Develop evaluation frameworks to assess and monitor system performance, accuracy, and reliability. Create and maintain production-grade AI applications featuring clean code, robust error handling, APIs, and data pipelines. Implement, maintain, and evaluate retrieval systems, including vector/graph databases and ingestion pipelines. Establish feedback loops and observability processes to enhance system performance continuously. Craft effective prompts and optimize for latency, cost, and quality across various model providers and configurations. Required Skills and Experience Hands-on experience building applications with LLM APIs and a deep understanding of their functionalities. Proficiency in software engineering principles and practices. Experience with production-grade system design, implementation, and optimization. Strong problem-solving skills and the ability to work collaboratively in a fast-paced environment. Familiarity with AI best practices and methodologies.