Our client, a very well-respected investment manager focused on private credit strategies, is seeking a full-time Senior AI Engineer to work fully onsite at their Greenwich, CT location.
The firm's focus includes Portfolio Debt Securities, Regulatory Capital Relief transactions, Infrastructure Credit, Strategic Credit investments and CLO securities. They manage billions on behalf of institutional and retail investors.
The ideal candidate will build and own production-grade LLM systems. You’ll design and operate core AI capabilities, model integrations, agentic workflows, retrieval, and evaluation, partnering with Business Intelligence and UX Engineers.
This is a hands-on role for engineers who have shipped real LLM systems and want deeper ownership and technical impact!
Responsibilities:
Own end-to-end LLM systems (RAG, agents, internal tools) from design to production
Make key decisions on prompting, retrieval, model selection, and system design
Build shared infrastructure (evals, prompt/versioning, pipelines, guardrails)
Define and run evals to measure quality and prevent regressions
Own latency, cost, reliability, and production incidents
Partner with frontend engineers on clean system interfaces
Raise the bar through code reviews, mentorship, and technical direction
Qualifications:
5+ years SWE experience, including 2+ years shipping LLM systems
Strong Python + one backend language (TypeScript, Go, Java, etc.)
Hands-on with LLM APIs (tool use, structured outputs, streaming, token trade-offs)
Experience with RAG (embeddings, vector DBs, chunking, ranking)
Strong evaluation mindset — you measure, not guess
Solid backend fundamentals (APIs, testing, CI/CD, observability)
Comfortable owning production trade-offs (cost, latency, reliability)
Clear communicator across technical and non-technical audiences