Member of Technical Staff — Post-Training Infrastructure

What you'll do

• Build RL and post-training pipelines, including systems for fine-tuning, preference optimization, reward modeling, and reinforcement learning.
• Create trajectory-data, reward, verification, and evaluation systems for long-horizon agent tasks.
• Scale distributed training and rollout generation, improving reliability, reproducibility, observability, and cost efficiency.

What they ask for

• Real-world experience training large language, vision-language, multimodal, or code models.
• Strong experience in reinforcement learning, post-training, or large-scale fine-tuning.
• Experience building distributed training or high-throughput inference systems.
• Strong Python skills and experience with PyTorch, JAX, or similar frameworks.

Nice to have

• Experience at a frontier AI lab or organization operating large-scale training systems.
• Experience with code-model post-training or autonomous coding agents.

Tools

Python, PyTorch, JAX

AI focus

Build training infrastructure and post-training methods for agents, including reinforcement learning, supervised fine-tuning, preference optimization, reward modeling, trajectory learning, and scalable evaluation; support agent, robotics, and embodied-model training.