Lead Agentic RL Scientist for Grounded LLMs

Thomson Reuters Corp.

Basel

Hybrid

CHF 130,000 - 190,000

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
Flex My Way
Career Development
Industry Competitive Benefits
Culture of inclusion
Social Impact

Job summary

Thomson Reuters Labs is seeking a Lead Research Scientist to drive agentic reinforcement learning and reward design for real-world, professional-domain tasks. You will lead research, innovate training signals, and publish results while mentoring engineers and collaborating across teams to scale models.

You will work with a global team, contribute to production-scale RL pipelines, and influence the direction of our frontier-scale LLMs in legal, tax, and compliance contexts.

Qualifications

  • PhD in machine learning, computer science or a related discipline.
  • 3+ years of research experience after the PhD, in industry or academia.
  • Strong publication record at top-tier venues (NeurIPS, ICML, ICLR, ACL, EMNLP, NAACL, COLM).
  • Hands-on experience post-training LLMs with RL or preference optimisation, using PyTorch (Advanced).
  • Proven experience mentoring or supervising researchers, engineers or students, and guiding their work to published or deployed results.

Responsibilities

  • Lead research direction: Own a research agenda in agentic RL and reward design, identify emerging methods, and roadmap for models.
  • Innovate: Create dense, reliable, cost-efficient training signals for real-world tasks.
  • Experiment rigorously: Design ablations and diagnostics, and translate results into production models.
  • Publish: Publish regularly as lead or senior author at top-tier venues and represent Thomson Reuters Labs.
  • Mentor and collaborate: Guide scientists and engineers, turning ideas into trained models at scale.
  • Communicate: Share findings through seminars, conferences, and released assets.

Skills

Research leadership
Experimental judgement
Mentorship
Communication
Self-direction

Education

PhD in machine learning or related field

Tools

PyTorch
NeMo-RL
OpenRLHF
TRL

Job description

Thomson Reuters Labs is seeking a Lead Research Scientist to drive agentic reinforcement learning and reward design for real-world, professional-domain tasks. You will lead research, innovate training signals, and publish results while mentoring engineers and collaborating across teams to scale models.

You will work with a global team, contribute to production-scale RL pipelines, and influence the direction of our frontier-scale LLMs in legal, tax, and compliance contexts.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Lead Agentic RL Scientist: Grounded LLMs & Tool Use
Lead Agentic RL Scientist: Grounded LLMs & Tool Use

Thomson Reuters • Zug

Hybrid
CHF 150,000 - 190,000
Hybrid work model
Flexible working arrangements
Career development programs
+2
Lead Research Scientist: Agentic RL for LLMs
Lead Research Scientist: Agentic RL for LLMs

Thomson Reuters • Zug

On-site
CHF 180,000 - 240,000
Lead Research Scientist, Agentic RL for LLMs
Lead Research Scientist, Agentic RL for LLMs

Thomson Reuters Corp. • Zug

On-site
CHF 180,000 - 240,000
Hybrid work model
Flexible vacation
Mental health days
+3
Lead Architect — Large-Scale RL for Agentic LLMs
Lead Architect — Large-Scale RL for Agentic LLMs

Thomson Reuters • Zug

On-site
CHF 150,000 - 210,000
Hybrid Work Model
Career Development
Mental Health Days / Wellbeing
Lead/Senior Research Scientist – Agentic Reinforcement Learning
Lead/Senior Research Scientist – Agentic Reinforcement Learning

Thomson Reuters • Zug

Hybrid
CHF 150,000 - 190,000
Hybrid work model
Flexible working arrangements
Career development programs
+2
Director of Frontier AI Research & Team Growth
Director of Frontier AI Research & Team Growth

Thomson Reuters • Zug

Hybrid
CHF 180,000 - 240,000
Hybrid Work Model
Flex My Way
Career Development
+4
Lead RL Architect for Frontier-Scale Agentic LLMs
Lead RL Architect for Frontier-Scale Agentic LLMs

Thomson Reuters Corp. • Basel

Hybrid
CHF 190,000 - 270,000
Hybrid Work Model
Flexible work arrangements
Career development and growth
Frontier AI Research Leader — Build & Grow Impactful Team
Frontier AI Research Leader — Build & Grow Impactful Team

Thomson Reuters • Zug

Hybrid
CHF 180,000 - 280,000
Hybrid Work Model
Flex My Way policy
Grow My Way skills development
+3
Lead/Senior Research Scientist – Agentic Reinforcement Learning
Lead/Senior Research Scientist – Agentic Reinforcement Learning

Thomson Reuters Corp. • Basel

Hybrid
CHF 130,000 - 190,000
Hybrid Work Model
Flex My Way
Career Development
+3
Lead/Senior Research Scientist – Agentic Reinforcement Learning
Lead/Senior Research Scientist – Agentic Reinforcement Learning

Thomson Reuters Corp. • Zug

Hybrid
CHF 120,000 - 180,000
Hybrid work model
Flexible vacation
Two Mental Health Days off
+5
Top locations