Lead Research Scientist, LLM Evaluation & Benchmarks

Thomson Reuters

Zug

Hybrid

CHF 140,000 - 210,000

Full time

2 days ago
Be an early applicant

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Benefits offered by this job

Hybrid work model
Flexible vacation
Mental health days
Tuition reimbursement

Job summary

Thomson Reuters Labs builds and ships custom models for professional workflows. We design, develop, optimize, and scale evaluation suites for fiduciary-grade AI and future Thomson LLM releases, collaborating with researchers and product teams to ensure robust, trusted model performance.

The role focuses on leading evaluation asset creation, mentoring researchers, and publishing findings at top AI conferences, with hybrid work options and a strong focus on real-world impact.

Qualifications

  • Hands-on research in evaluations with designing, building and releasing benchmarks for frontier models or agents; publications in top AI conferences.
  • Experience translating ideas into practical evaluations with researchers and cross-functional stakeholders.
  • Hands-on Python coding for benchmarks, agents or systems built around LLMs.
  • Familiarity with current developments in LLMs; staying up to date with evolving frontier.

Responsibilities

  • Build and operate the evaluation suite that runs Thomson evaluations; create new evaluations for gaps in coverage.
  • Lead cross-functional teams of scientists, engineers, and subject-matter experts on evaluations and benchmarks; mentor junior scientists.
  • Inform technical direction and trade-offs in model development; contribute to training objectives.
  • Publish research findings in top AI/ML/NLP conferences and integrate findings into products.

Skills

Evaluation research
Benchmarks design
Publications in AI conferences
Cross-functional collaboration
Python benchmarking

Education

PhD in CS or related field

Tools

Python
Benchmark tooling

Job description

Thomson Reuters Labs builds and ships custom models for professional workflows. We design, develop, optimize, and scale evaluation suites for fiduciary-grade AI and future Thomson LLM releases, collaborating with researchers and product teams to ensure robust, trusted model performance.

The role focuses on leading evaluation asset creation, mentoring researchers, and publishing findings at top AI conferences, with hybrid work options and a strong focus on real-world impact.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Lead Research Scientist, Model Evaluations & Benchmarks
Lead Research Scientist, Model Evaluations & Benchmarks

Thomson Reuters Corp. • Basel

Hybrid
CHF 150,000 - 190,000
Senior Research Engineer, Model Evaluations — Scale & Optimize
Senior Research Engineer, Model Evaluations — Scale & Optimize

Thomson Reuters • Zug

Hybrid
CHF 120,000 - 180,000
Hybrid Work Model
Flexible vacation
Mental Health Days off
+3
Senior AI Evaluation Engineer - LLM Benchmarks & Scale
Senior AI Evaluation Engineer - LLM Benchmarks & Scale

Thomson Reuters • Zug

Hybrid
CHF 120,000 - 170,000
Hybrid Work Model
Flex My Way
Grow My Way
+1
Lead Research Scientist, AI Evaluation & Benchmarks
Lead Research Scientist, AI Evaluation & Benchmarks

Thomson Reuters Corp. • Zug

Hybrid
CHF 140,000 - 200,000
Senior Research Engineer, Model Evaluations
Senior Research Engineer, Model Evaluations

Thomson Reuters • Zug

Hybrid
CHF 120,000 - 170,000
Hybrid Work Model
Flex My Way
Grow My Way
+1
Senior/Lead Research Scientist, Model Evaluations
Senior/Lead Research Scientist, Model Evaluations

Thomson Reuters • Zug

Hybrid
CHF 140,000 - 210,000
Hybrid work model
Flexible vacation
Mental health days
+1
Head of Frontier AI Research
Head of Frontier AI Research

Thomson Reuters Corp. • Basel

Hybrid
CHF 180,000 - 240,000
Senior/Lead Research Scientist, Model Evaluations
Senior/Lead Research Scientist, Model Evaluations

Thomson Reuters • Zug

Hybrid
CHF 140,000 - 210,000
Hybrid Work Model
Flex My Way
Grow My Way
+4
Senior Research Engineer, Model Evaluations
Senior Research Engineer, Model Evaluations

Thomson Reuters • Zug

Hybrid
CHF 120,000 - 180,000
Hybrid Work Model
Flexible vacation
Mental Health Days off
+3
Senior/Lead Research Scientist, Model Evaluations
Senior/Lead Research Scientist, Model Evaluations

Thomson Reuters Corp. • Zug

Hybrid
CHF 140,000 - 200,000
Top locations