Thomson Reuters
Staff Software Engineer
$118K–$220K
United States of America, Eagan, Minnesota +2 · 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, Ann Arbor, Michigan - Experience
- 7+ years of software engineering experience, including 2+ years in technical leadership roles and 3+ years building scalable cloud applications, APIs, and AI-enabled products.
- Education
- BA or BS in Computer Science or equivalent practical experience.
About the job
Lead technical direction and delivery of scalable, production-ready AI agentic features for CoCounsel legal products, including backend services and agent interfaces.
What you'll do
- Architect and build AI agent systems, backend services, and scalable platform patterns.
- Lead technical strategy, experimentation, testing, rollout, and operational excellence for AI products.
- Mentor engineers and partner with Labs, product, design, and engineering leaders to productionize AI capabilities.
What they ask for
- Strong proficiency in Python, FastAPI, PostgreSQL, and AWS or Azure cloud services.
- Experience building and owning CI/CD pipelines for production web applications, including automated testing and safe releases.
- Proven experience shipping production-grade AI systems, including deployment, monitoring, evaluation, scaling, and operational ownership in enterprise environments.
- Strong technical leadership, mentoring, communication, and problem-solving skills.
Nice to have
- Knowledge of vector databases, embeddings, semantic search, and information retrieval; experience with AG-UI or comparable protocols and SSE.
- Experience with Datadog, CloudWatch Log Insights, Braintrust, or products in legal, compliance, or other regulated domains.
Pay
$118,400 USD - $219,800 USD (base salary)
Tools
Python, FastAPI, PostgreSQL, AWS, Azure, GitHub Actions, GitLab CI, CodePipeline
AI focus
Build and productionize agentic legal software, including LLM orchestration, agentic workflows, content pipelines, AI evaluation, provider integrations, guardrails, and observability.
Model-written summary · the original posting is authoritative