Research Fellowship - Automated Environment Design

Research Fellowship - Automated Environment Design About V max

V max is an applied research lab working at the frontier of reinforcement learning (RL). We are building new techniques for leveraging RL with Large Language Models (LLMs). Our research contributes directly to our RL platform, which automates the engineering involved in converting data and evals into RL environments.

This position is for a 6-month research project with the V max team to make progress on our environment generation techniques.

To scale RL we must scale the creation of environments that are tractable for agents to learn from, and that capture the full richness and variety of the tasks an agent is expected to perform. We are looking for scientists to join us in developing this novel program of AI research - applying the principles of RL to environment generation and post-training itself.

• Develop optimization-based methods for automatically generating RL environments
• Establish normative baselines for measuring the quality of RL environments

• Currently enrolled in a PhD or equivalent experience
• Track record of research excellence, as demonstrated by publications, open source work or publicly deployed AI systems
• Deep understanding of RL and ML
• Expertise with Python and a ML framework (PyTorch, JAX) is required for this role as well as experience with post-training frameworks

• Experience in post-training LLMs
• Experience researching unsupervised environment design

• This role is based in our San Francisco office; for exceptional candidates we are willing to consider a hybrid arrangement