Principal Applied Scientist - Coreai

Microsoft Microsoft · Big Tech · Redmond, WA +4 · Applied Sciences

This role focuses on building and scaling agentic retrieval systems for enterprise customers, integrating state-of-the-art LLM techniques and AI coding agents into production. The work involves developing LLM prompts, agents, and query execution workflows, often with latency constraints, and improving knowledge retrieval quality through techniques like RAG and agentic engines.

What you'd actually do

  1. Lead state of the art research incorporation into techniques shipped to production.
  2. Proactively develop and build metrics to use across the full range of search engine components.
  3. Seek out and incorporate customer feedback into dataset construction, evaluation, and technique development.
  4. Lead technical excellence and contribute to experimentation infrastructure and proofs-of-concept using AI coding agents.
  5. Advances the quality of the team’s experimental codebase to ensure experiments are efficient and repeatable.

Skills

Required

  • Bachelor's Degree in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND 6+ years related experience OR Master's Degree in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND 4+ years related experience OR Doctorate in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND 3+ years related experience OR equivalent experience.

Nice to have

  • Master's Degree in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND 9+ years related experience OR Doctorate in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND 6+ years related experience OR equivalent experience.
  • 3+ year(s) experience developing and deploying products or systems at multiple points in the product cycle from ideation to shipping.
  • Experience with agentic coding systems, including scaffolding for long-running agents.

What the JD emphasized

  • required
  • production at scale
  • state of the art research incorporation into techniques shipped to production
  • AI coding agents

Other signals

  • developing LLM prompts, agents and query execution workflows
  • building off state of the art techniques
  • agentic retrieval engine
  • Foundry IQ
  • knowledge bases
  • leveraging multiple coding agents to explore new techniques
  • bring them to production at scale