Member of Technical Staff — Agent Post-Training

What you'll do

• Build RL and post-training pipelines, including infrastructure for fine-tuning, preference optimization, and reward modeling.
• Develop systems to collect and learn from agent trajectories, and create rewards, verifiers, and evaluations for long-horizon tasks.
• Scale distributed training and rollout generation while 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, autonomous coding agents, multimodal models, robotics, simulation, or embodied AI.

Tools

Python, PyTorch, JAX

AI focus

Train and post-train multimodal agents using supervised fine-tuning, preference optimization, reward modeling, and reinforcement learning; improve agents’ planning, coding, tool use, and performance on complex tasks, including robotics and embodied-model training.