Vmax

Member of Technical Staff - Mechanistic Interpretability

San Francisco · Staff+

Sponsorship not specified$300k-$500kDetected 62 days ago

PythonMachine LearningPyTorchLLMsResearch

About the role

LLMs are fantastically powerful and there is a rapidly growing corpus of work devoted to understanding their internal representations and computations.
We use the tools of mechanistic interpretability to enhance reinforcement learning by generating intrinsic rewards as a supplement or alternative to downstream human-generated verifiers.

Develop methods for using mechanistic interpretability to extract useful training signals from the internal states of language models.
Design metrics and baselines for reward quality, including alignment with intended behavior, generalization across tasks, robustness, and resistance to reward hacking.
Develop infrastructure for reproducible, large-scale experiments on LLM agents, interpretability tools, and RL environments.
Experience designing and running rigorous ML experiments, including ablations, baselines, evaluation design, and failure analysis.

Track record of research excellence, as demonstrated by publications, open source work, deployed AI systems, or other substantial technical contributions.
Expertise with Python and at least one major ML framework such as PyTorch or JAX.
Ability to work independently on open-ended research problems and turn ambiguous ideas into concrete experimental programs.

Experience with mechanistic interpretability techniques such as activation patching, probing, sparse autoencoders, feature attribution
Experience training or evaluating language-model agents in interactive, tool-using, or multi-step reasoning settings.
Familiarity with scalable RL infrastructure, distributed training, experiment tracking, and large-scale evaluation pipelines.
Demonstrated software engineering ability, especially in research codebases that require reliability, reproducibility, and iteration speed.
Ability to present technical results and their strategic implications to both research and non-research audiences.
This role is based in our San Francisco office

Turn representations, features, circuits, and causal model behaviors into intrinsic rewards for reinforcement learning.
Define and pursue a high-impact research agenda that advances Vmax's goal of open-ended learning beyond imitation of human expertise.
PhD or equivalent experience in machine learning, reinforcement learning, or a closely related field.
Deep understanding of modern machine learning, especially reinforcement learning, representation learning, and large language models.

V max is an applied research lab developing AI capable of open-ended learning.
We are building systems to exceed humans in all capacities by optimising beyond the local maxima of learning from human expertise.

This listing is sourced directly from Vmax's careers page and normalized into a canonical job model.