Production-Grade AI Evaluation & Benchmarking Lead

CAN002 Thomson Reuters Canada Ltd; Eagan (MN); Hybride; USD 127 000 - 237 000; Plein temps

Avantages offerts par ce poste

Hybrid work model

Health and wellness benefits

Résumé du poste

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 infra to compare large language models, measure quality, cost, and latency, and guide the engineering direction from prototypes to maintainable tools.

You will partner with research scientists and product teams, own the engineering roadmap, and mentor engineers while addressing performance and cost challenges in a hybrid

Qualifications

• 8–10+ years of software engineering experience.
• Strong Python programming, API design, automated testing, and data handling.
• Technical leadership and end-to-end delivery experience.
• Experience collab orating with researchers to translate experiments into software.
• Cloud engineering experience using AWS/Azure with distributed workflows.
• Working knowledge of SQL and processing structured/unstructured data.
• Excellent collaboration and mentoring across teams.
• Bachelor’s degree in CS, Engineering, or related field or equivalent experience.

Responsabilités

• Lead technical delivery and engineering planning across programs.
• Design and build scalable evaluation infrastructure with Python services.
• Deliver initial versions, validate with users, and iterate.
• Turn research methods into working software with automated pipelines.
• Implement reliable workflows to compare LLMs and AI models.
• Maintain repeatable experiments with traceable results.
• Measure model quality, cost, and latency for product teams.
• Develop clear user interfaces, documentation, and evaluation reports.
• Own production reliability, deployment, and monitoring.
• Mentor engineers and align delivery with stakeholders.

Connaissances

Python

API design

Automated testing

Cloud (AWS/Azure)

SQL

End-to-end delivery

Mentoring

Collaboration

Research collaboration

Formation

Bachelor’s degree in CS, Engineering, or related field

Description du poste

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 infra to compare large language models, measure quality, cost, and latency, and guide the engineering direction from prototypes to maintainable tools.

You will partner with research scientists and product teams, own the engineering roadmap, and mentor engineers while addressing performance and cost challenges in a hybrid