Agent Post-Training Research Scientist β€” RL & AI

Agent Post-Training Research Scientist β€” RL & AI

Full-Time 70000 - 90000 Β£ / year (est.) No working from home possible
Software Careers

At a Glance

  • Tasks: Design experiments and build infrastructure for cutting-edge AI research.
  • Company: Join DeepMind, a leader in AI innovation based in London.
  • Benefits: Competitive salary, flexible working hours, and opportunities for professional growth.
  • Other info: Collaborative environment with a focus on groundbreaking technology.
  • Why this job: Be at the forefront of AI research and make a real-world impact.
  • Qualifications: Experience in AI, research skills, and a passion for innovation.

The predicted salary is between 70000 - 90000 Β£ per year.

Deep Mind in London, UK, is seeking a Research Scientist (Post-Training) or Research Engineer to push the frontier of agentic tasks in post-training LLMs.

You will design scalable experiments and build infrastructure for tool use and RL in Gemini post-training.

You will lead from hypothesis to impact, collaborate with researchers and engineers, and communicate results through clear plots and reports.

Software Careers

Contact Details:

Software Careers Recruitment Team

We think you need these skills to ace Agent Post-Training Research Scientist β€” RL & AI

Python
SQL
Problem-Solving Skills
Communication Skills
Attention to Detail
Data Engineering
Data Pipeline Development