About the role

We're hiring a Machine Learning Engineer to help build and ship LLM-powered features for enterprise customers in regulated industries. You'll work closely with our senior engineers and data team to turn prototypes into reliable production services — writing the retrieval logic, evaluation code, and APIs that real users depend on.

What you'll do

• Implement and maintain retrieval-augmented generation (RAG) pipelines against customer knowledge bases.
• Write evaluation harnesses and regression tests that catch quality drops before they reach production.
• Build and own backend services and APIs that wrap LLM workflows.
• Profile and tune systems for latency, cost, and accuracy under real load.
• Collaborate with data engineers on the vector indexes and pipelines your models rely on.

What you'll bring

• 2+ years of production software or ML engineering experience.
• Strong Python and comfort with the modern AI stack (LangChain, LlamaIndex, vector databases, OpenAI / Anthropic APIs).
• Solid software fundamentals: testing, version control, code review, and clean APIs.
• A practical mindset about trade-offs between speed, cost, and quality.

Nice to have

• Exposure to evaluation tooling (LangSmith, Arize, or similar).
• Experience with cloud ML platforms (Azure ML, AWS Bedrock, GCP Vertex AI).
• Interest in working with regulated data (healthcare, financial services, public sector).