Thomson Reuters
Staff Software Engineer – AI Platform
$137K–$293K
United States of America, Eagan, Minnesota +4 · Hybrid · Staff · Full-time · Posted Oct 21, 2026
- Location
- United States of America, Eagan, Minnesota
United States of America, Frisco, Texas
United States of America, Brooklyn, New York
Canada, Toronto, Ontario
United States of America, Ann Arbor, Michigan - Experience
- 5-7+ years.
- Education
- Bachelor’s degree in computer science, Computer Engineering, a related field, or equivalent experience.
About the job
Own and lead the backend and AI orchestration platform for CoCounsel for Audit, turning AI models into reliable, scalable workflows for accountants.
What you'll do
- Lead cross-functional, multi-quarter initiatives; mentor engineers and shape technical strategy.
- Design and build backend services and orchestration for AI agents, workflows, and document-centric products.
- Improve scale, reliability, and performance through retrieval, observability, resilience, and incident response.
What they ask for
- Bachelor’s degree in computer science, Computer Engineering, a related field, or equivalent experience.
- 5-7+ years of experience in full-stack development building scalable cloud applications, web services, APIs, and AI-driven products.
- Deep Python expertise and production experience with FastAPI or similar, PostgreSQL or equivalent, and a major cloud provider.
- Distributed-systems expertise and a track record leading complex projects end-to-end.
Nice to have
- Production LLM API integration experience, including prompt/response management, cost controls, and safety.
- Experience with vector databases, embeddings, semantic search, retrieval pipelines, or correctness-sensitive domains.
Pay
$158,000 USD - $293,000 USD base salary (eligible listed office locations); $137,100 USD - $254,700 USD base salary (other eligible US locations).
Tools
Python, FastAPI, PostgreSQL, AWS, Vercel, OpenAI, Anthropic
AI focus
Build and lead AI agents and orchestration, including MCP servers, tool calling, multi-step workflows, retrieval, safety, and production integration of LLMs.
Model-written summary · the original posting is authoritative