Member of Technical Staff

Member of Technical Staff at dmodel, an AI research lab. This role focuses on building reinforcement learning environments and evaluations to study AI agent alignment. Responsibilities include developing robust graders, finding novel interpretability and alignment techniques, running experiments, and investigating AI interpretability within RL environments.

Skills and focus areas

• python
• ml frameworks
• reinforcement learning
• ai safety
• interpretability
• specification gaming
• research
• experimentation
• model behavior analysis
• collaboration
• pytorch
• jax