Member of Technical Staff - RL Algorithms

What you'll do

• Develop RL algorithms and adapt pre-LLM methods for LLM and agentic settings.
• Design evaluation protocols and analyze sample efficiency, robustness, generalization, and model failure modes.
• Own a research agenda and collaborate across research and infrastructure teams to build reliable training systems.

What they ask for

• PhD or equivalent experience in machine learning, reinforcement learning, or a closely related field.
• Research excellence demonstrated through publications, open-source work, deployed AI systems, or other substantial technical contributions.
• Deep understanding of modern machine learning, including RL, representation learning, and LLMs; strong familiarity with LLM post-training methods.
• Experience running rigorous ML experiments and working with large-scale ML infrastructure; expertise in Python and PyTorch or JAX.

Nice to have

• Experience developing RL algorithms in areas such as robotics, games, simulated control, language models, or agents.
• Experience with LLM pre-training; reward modeling, verifiers, supervision, or automated evaluation; or demonstrated software engineering ability.

Pay

$300,000 - $500,000 USD (base salary)

Tools

Python, PyTorch, JAX

AI focus

Research and develop reinforcement-learning algorithms for LLM post-training, including adapting pre-LLM methods and evaluating model behavior and failure modes.