Research Scientist, RL for Long-Horizon Agents

General Reasoning, Inc.; Greater London; Sur place; GBP 70 000 - 90 000; Plein temps

Résumé du poste

A leading AI research firm in London is seeking a Research Scientist to push the frontier of reinforcement learning. The role involves designing, implementing, and evaluating novel RL methods for language models and requires experience in reinforcement learning and proficiency in Python. You will collaborate closely with engineering teams, run large-scale experiments, and publish findings to contribute to the advancement of AI. A competitive salary package is offered in a fast-paced research environment.

Qualifications

• Strong background in reinforcement learning: policy gradient methods, value-based methods, PPO, or related algorithms.
• Proficiency in Python and ML frameworks with the ability to implement and run experiments independently.
• Evidence of extraordinary accomplishment in work or early life.

Responsabilités

• Design and implement novel RL algorithms and training methodologies for long-horizon agents.
• Run RL training experiments at scale and analyse agent behaviour.
• Collaborate with engineering teams to bring research innovations into production.

Connaissances

Reinforcement learning

Python

ML frameworks (PyTorch or JAX)

Policy gradient methods

Value-based methods

Description du poste

A leading AI research firm in London is seeking a Research Scientist to push the frontier of reinforcement learning. The role involves designing, implementing, and evaluating novel RL methods for language models and requires experience in reinforcement learning and proficiency in Python. You will collaborate closely with engineering teams, run large-scale experiments, and publish findings to contribute to the advancement of AI. A competitive salary package is offered in a fast-paced research environment.