Skip to content
Back to jobs

Lead/Senior Research Scientist – Agentic Reinforcement Learning

  • Thomson Reuters
  • Switzerland, Zug, Zug, Switzerland
  • Level:Team Lead
  • Hybrid
  • Posted

Source: Thomson Reuters’s own career site First seen

Open original posting (opens in a new tab)

About the job

Job Description. Are you a curious and rigorous researcher who wants to push the frontier of how large language models (LLMs) learn to act? Thomson Reuters Labs is seeking a Lead Research Scientist to drive research on agentic reinforcement learning (RL): finding new, efficient ways to obtain reliable training signals for complex, multi-step tasks in professional domains such as legal, tax and…

This is a short extract. Read the full posting and apply on the employer’s site.

See how well you fit this job

Log in and we compare this role with your CV: where you are a strong fit, where you are not, and what is worth saying about the gaps. You can also prepare a CV and cover letter written for this role.