AI Research Engineer

About the role

Design and execute post-training workflows for foundation models using reinforcement learning and alignment techniques.

Skills

• Reinforcement Learning must have
• Policy Gradient Methods must have
• Reward Modeling must have
• Distributed Training must have
• Preference Optimization must have
• Ray must have
• vLLM must have
• DeepSpeed must have
• JAX must have
• PyTorch must have