Vmax
Member of Technical Staff - Open Endedness
$300K–$500K
San Francisco +1 · Staff · Full-time · Posted Nov 5, 2025
- Location
- San Francisco
San Francisco, California, United States - Education
- PhD or equivalent experience in machine learning, reinforcement learning, artificial intelligence, or a closely related field.
About the job
Develops reinforcement-learning methods and systems that enable agents to discover objectives, tasks, and curricula for open-ended learning.
What you'll do
- Develop RL methods and training systems using nonstandard reward signals, exploration, and self-generated challenges.
- Investigate ways to prevent agents from converging on trivial, degenerate, or exploitable objectives.
- Lead a research agenda, including experiment design, execution, and communicating results.
What they ask for
- PhD or equivalent experience in machine learning, reinforcement learning, artificial intelligence, or a closely related field.
- Strong technical track record and deep understanding of reinforcement learning.
- Experience with LLM post-training and strong empirical research ability.
- Strong programming ability in Python and experience with PyTorch or JAX.
Nice to have
- Experience with open-ended learning, intrinsic motivation, self-play, curriculum generation, or related methods.
- Experience designing benchmarks or evaluations for generalization, exploration, long-horizon learning, or behavioral diversity.
Pay
$300,000 - $500,000 USD (base salary)
Tools
Python, PyTorch, JAX
AI focus
Research and develop agents that discover their own objectives, tasks, and curricula through open-ended learning and reinforcement learning.
Model-written summary · the original posting is authoritative