The Effective Altruism
Opportunities Board
Work on the world's most pressing problems. Browse jobs, fellowships, internships, courses, and more at high-impact organisations.
Research Associate, Safe Reinforcement Learning
Imperial College LondonLondon, UK
London, UK
Today
Deadline
2026-09-20
Routes to impact
Direct high impact on an important cause
Description
Conduct postdoctoral research on formal methods for safe reinforcement learning in safety-critical cyber-physical systems.
- Develop Safe RL algorithms using formally verifiable proof certificates
- Research monitoring and shielding methods for cyber-physical systems
- Contribute to the open-source MASA-Safe-RL library
- Collaborate across reinforcement learning, formal methods, and multi-agent systems
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.
Related opportunities
PhD Position, Responsible Machine Learning
ELLIS Institute TübingenVienna, Austria
Vienna, Austria
Yesterday
Research Engineer / Research Scientist, Misuse Red Team
AI Security Institute (AISI)London, UK
London, UK
6 days ago
Research Scientist
ResolutionBerkeley, CA / London, UK / Remote
Berkeley, CA / London, UK / Remote
2 months ago
Lean Proof Contractor
DovetailRemote (United Kingdom)
Remote (United Kingdom)
4 months ago
Research Engineer
FAR.AIBerkeley, USA / Remote
Berkeley, USA / Remote
4 months ago
Research Scientist
FAR.AIRemote / Berkeley, USA
Remote / Berkeley, USA
4 months ago
Research Staff – AI Safety & Secure Deep Learning
Dawn Song (UC Berkeley)Berkeley, USA
Berkeley, USA
10 months ago
The SandboxAQ Residency Program
SandboxAQRemote / Palo Alto, USA
Remote / Palo Alto, USA
8 months ago
Join 60k subscribers and sign up for the EA Newsletter, a monthly email with the latest ideas and opportunities