About the job
About the Role
We are seeking a talented AI Engineer to develop cutting-edge production-grade AI systems, focusing on agent architectures, applications powered by large language models (LLMs), and scalable API integrations. This position requires a combination of technical expertise and client-facing collaboration.
You will be responsible for designing intelligent agents, deploying advanced AI services, and engaging directly with both internal teams and external clients to turn business challenges into scalable AI solutions.
This is a hands-on role that offers substantial ownership and visibility within the organization.
A Day in the Life
AI and Agent Systems
- Create and implement AI agents that are capable of reasoning, planning, and executing tasks.
- Develop multi-step agent workflows with memory and state management.
- Build production-ready retrieval-augmented generation (RAG) systems with optimized retrieval and context handling.
- Refine and assess LLMs for specific domain applications.
- Establish guardrails, validation layers, and structured output controls.
- Design evaluation frameworks aimed at reliability, hallucination mitigation, and safety.
Backend and Platform Engineering
- Create scalable REST APIs to provide AI functionalities.
- Integrate AI agents with enterprise applications and third-party systems.
- Design microservices and asynchronous systems for high throughput workloads.
- Enhance inference latency, reliability, and cloud cost efficiency.
- Implement monitoring, logging, and observability for AI services.
Consulting and Client Engagement
- Interact directly with clients to gather business requirements and translate them into AI-driven solutions.
- Lead technical discovery meetings and solution workshops.
- Effectively communicate complex AI concepts to non-technical stakeholders.
- Provide architectural advice and implementation roadmaps.
- Support pilot projects, proofs of concept, and production deployments.
