About the job
Note: Cornspring is unable to sponsor visas in the UK. Candidates applying for London must hold the right to work in the UK.
Cornspring is a pioneering FinTech startup dedicated to empowering Family Offices and Asset Owners with cutting-edge, AI-driven data intelligence and portfolio insights.
We are addressing one of the most intricate and valuable challenges in finance. Our clients navigate the highest echelons of global markets, managing billions in assets, while often hindered by outdated legacy systems that are inefficient and fragmented.
At Cornspring, we are revolutionizing Family Office services by leveraging state-of-the-art generative AI and Large Language Models (LLMs) to optimize investment, accounting, and operational data. Our platform ensures swifter insights, enhanced transparency, and innovative methods of engaging with financial information.
Your Role
We seek a remarkable Senior Software Engineer, proficient in ML and LLM, with a proven track record in building production-grade AI systems from concept to implementation.
This is a critical position where you will influence the core system architecture, design and deploy AI-driven functionalities, and engage hands-on with backend systems and applied LLM development. You will hold significant responsibility for technical decisions and have a direct impact on mission-critical products utilized by sophisticated financial clients.
If you have a passion for creating scalable systems, deploying LLMs in live production settings, and thrive in a high-caliber engineering environment, we would be excited to connect with you.
Key Responsibilities
Backend Engineering & Architecture
- Design, build, and optimize scalable backend systems in Azure, employing Python, containers, FastAPI, and contemporary architectural methodologies.
- Take full ownership of services throughout their lifecycle: from initial concept and design to deployment, monitoring, and iterative improvement.
- Enhance performance and reliability through code refactoring, algorithmic enhancements, asynchronous processing, and strategic caching.
- Operate swiftly by rapidly prototyping, assessing results, scaling successful strategies, and adjusting as needed.
- Work collaboratively with product and data teams to translate complex financial and AI requirements into robust, production-ready features.
ML, AI & LLM Systems
- Design and implement LLM-driven features utilizing both SaaS and locally hosted models.
- Develop and refine Retrieval-Augmented Generation (RAG) pipelines for both structured and unstructured financial data.
- Utilize HuggingFace, vLLM, prompt engineering, and model orchestration frameworks to deliver sophisticated AI solutions.
- Establish comprehensive evaluation, testing, and monitoring protocols for LLM outputs, prioritizing correctness, determinism, latency, and cost efficiency.
