Reinforcement Learning Engineer
Negotiable
Descrição da vaga
Develop reinforcement learning systems for training and aligning AI models. Work on RLHF and advanced RL techniques.
Requisitos
- MSc/PhD in ML, Robotics, or related
- 3+ years RL experience
- Strong knowledge of policy optimization
- Experience with RLHF, PPO, DPO
- Proficient in Python and RL frameworks
- Research publications a plus
- 3+ years RL experience
- Strong knowledge of policy optimization
- Experience with RLHF, PPO, DPO
- Proficient in Python and RL frameworks
- Research publications a plus
Responsabilidades
- Implement RL training pipelines
- Develop reward modeling systems
- Optimize RL algorithms
- Collaborate with safety team
- Research new RL techniques
- Document and share learnings
- Develop reward modeling systems
- Optimize RL algorithms
- Collaborate with safety team
- Research new RL techniques
- Document and share learnings
Benefícios
- Salary £80,000 - £125,000
- Research-focused role
- Conference attendance
- Stock options
- Premium benefits
- Gym membership
- Research-focused role
- Conference attendance
- Stock options
- Premium benefits
- Gym membership
Visão geral da vaga
Tipo de emprego
Tempo integral
Nível de experiência
Pleno
Localização
London, England, United Kingdom
Vagas
2
Candidatar-se agora