AI Evaluation & Benchmarking Lead Engineer

Thomson Reuters; Eagan (MN); Hybrid; USD 127,000 - 273,000; Full time

Benefits offered by this job

Hybrid Work Model

Career Development and Growth

Industry Competitive Benefits

Job summary

Thomson Reuters Labs seeks a Lead Research Engineer to design and deliver production-ready software for AI model evaluation and benchmarking. You will build scalable evaluation infrastructure to compare LLMs, measure quality, cost, and latency, and guide model selection.

You will own the engineering approach from prototypes to reliable tools, collaborating with researchers, engineers, and product partners. The role combines technical leadership, end-to-end delivery, and responsible data use,

Qualifications

• 8–10+ years of software engineering experience with production systems.
• Hands-on Python programming, API design, automated testing.
• Experience leading end-to-end delivery and architecture decisions.
• Collaboration with researchers or ML practitioners to translate experiments into software.
• Knowledge of language models and evaluation methods; identify data leakage risks.

Responsibilities

• Lead technical delivery and engineering planning with stakeholders.
• Design and build scalable evaluation infrastructure and reusable tools.
• Turn research methods into working software and automated pipelines.
• Ensure reproducible model comparisons with traceability of inputs and methods.
• Build user interfaces, docs, reports, and diagnostic capabilities for researchers.
• Own production reliability, deployment, monitoring, and data access controls.

Skills

Python

API design

Automated testing

Technical leadership

Cross-team collaboration

Education

Bachelor's degree in Computer Science or related field

Tools

AWS

Azure

Distributed workflows

Monitoring

Job description

Thomson Reuters Labs seeks a Lead Research Engineer to design and deliver production-ready software for AI model evaluation and benchmarking. You will build scalable evaluation infrastructure to compare LLMs, measure quality, cost, and latency, and guide model selection.

You will own the engineering approach from prototypes to reliable tools, collaborating with researchers, engineers, and product partners. The role combines technical leadership, end-to-end delivery, and responsible data use,