Senior Research Engineer, Model Evaluations
Core
Design, develop, optimize, and scale evaluation suites for Thomson Reuters' professional LLMs to assess performance on complex legal and professional workflows.
Role type
Senior Research Engineer (Model Evaluations)
Builds
Evaluation suite and platform for Thomson model releases
Domain
Legal technology / Professional AI / LLMs
Deliverable
production ML models
Required skills
Research engineering, building/scaling/optimizing evaluation suites, cross-functional collaboration, system reliability, LLM system design
Preferred skills
Evaluation frameworks (Inspect, Harbor, lm-evaluation-harness), AI-assisted coding, coding agents
Technologies
Thomson LLM family, multi-agent systems, decision models
Responsibilities
Build and operate the evaluation suite, design and develop the platform to scale, implement optimization techniques for cost and latency, contribute to ISO 27001 compliance, work with the evaluation pod for new model releases
Seniority
Senior, hands-on IC