As a Member of Technical Staff, you will build frameworks to improve the reasoning capability, build distributed reinforcement learning systems, techniques for inference time compute (e.g. tree search and planning), and develop environments for agents.
What you'll do
- Build robust and scalable distributed RL systems.
- Optimize frameworks to enable complex inference-time reasoning.
- Develop environments and harnesses for agents.
What you need
- Experienced with large-scale reinforcement learning systems.
- Designing and implementing distributed systems.
- Keeping up with state-of-the-art RL and inference time compute algorithms.
