AI / applied ML engineer

Role overview

Improve the quality and reliability of an applied AI product by refining retrieval, evaluation, and model routing. The focus is production-oriented machine learning: making measurable improvements without adding unnecessary complexity.

Responsibilities - Improve information retrieval quality in deployed LLM applications. - Develop or refine evaluation methods for models and application behavior. - Improve how requests are routed among models. - Focus work on measurable gains and production usefulness rather than isolated demos.

Requirements - Experience building or operating LLM applications, embedding-based systems, or evaluation harnesses in production. - Python experience and willingness to work in TypeScript when needed. - A practical, measurement-driven approach to applied machine learning.

Benefits and work setup

Full-time role with remote work. The listing indicates a 3+ years experience level.