About the role
Member of Technical Staff, Automated Environment Design
About Vmax
Vmax 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.
About the role
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.
Responsibilities
- Develop optimization-based methods for automatically generating RL environments
- Establish normative baselines for measuring the quality of RL environments
- Create infrastructure to reliably generate environments that incorporate historical data and agentic evals
- Own and develop a research agenda within Vmax
Minimum Requirements
- AI 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 an ML framework (PyTorch, JAX)
Nice to have
- Experience with LLM post-training
- Demonstrated software engineering experience
- Skilled in presenting the results and implications of your work to multiple audiences
Role specific location policy
