Member of Technical Staff, RL Infra

You will design and optimize infrastructure for large-scale reinforcement learning and post-training workloads. You will improve distributed pipeline reliability and throughput and create monitoring and observability tools for stable, debuggable, reproducible RL systems.

Responsibilities

• Build infrastructure for large-scale reinforcement learning and post-training workloads
• Improve reliability and scalability of distributed reinforcement learning pipelines
• Improve training throughput for reinforcement learning workloads
• Develop monitoring and observability tools for reinforcement learning systems

Requirements

• PyTorch
• TensorFlow
• Ray
• Megatron
• Reinforcement learning
• PPO
• DPO
• RLHF
• Reward modeling
• Docker
• Kubernetes
• CI/CD

Benefits

• Equity
• Flexible vacation and paid time off
• Health insurance
• Dental insurance
• Vision insurance
• 401k match
• Catered meals
• Commuter subsidies