SF-based startup helping enterprises discover and validate AI transformation initiatives

AI Engineer

San FranciscoOn-site$180K - $250K3 - 8 years
You'll spend mornings debugging retrieval pipelines that surface the right context from messy enterprise documents, then prototype agents in Python before translating the stable parts to TypeScript services that ship to production by afternoon. This team builds systems that executives actually trust—meaning your work balances bleeding-edge LLM orchestration with the unglamorous rigor of eval suites, cost tracking, and fallback logic when models hallucinate. The code you write ships daily to AWS infrastructure serving billion-dollar companies who need proof that AI spend translates to measurable outcomes.

What they're looking for

  • 3+ years shipping production ML systems, including at least one LLM or embedding-based application in Python or Node.js
  • Proficiency with vector databases and retrieval architecture— you've tuned chunking strategies and re-ranking to hit recall targets
  • Demonstrated comfort across the stack: prototype in Python, productionize in TypeScript, deploy on AWS without handoff friction
  • Experience with evaluation frameworks and safety guardrails for customer-facing AI products, not just internal tools
  • Strong written communication; you'll present technical tradeoffs to non-technical buyers and document decisions for a small, distributed team

Tech stack

TypeScriptNodeJSPythonAWSOpenAIVector DatabaseLangchain

Apply for this role

This role is one we're recruiting for on behalf of a client company; the client's identity is kept confidential at this stage. A Fluency recruiter will follow up with details.