Research Fellowship - Mechanistic Interpretability
SFFull-timePosted 3mo ago
About the role
3 to 6 month fellowship for PhD students or equivalent early-career researchers at the intersection of mechanistic interpretability and reinforcement learning, with ownership of a focused research project and opportunities to contribute to publications.
Responsibilities
- Develop mechanistic interpretability methods for understanding internal representations, features, circuits, and computations in language models and agents.
- Investigate how model internals can be used to generate intrinsic rewards, auxiliary objectives, diagnostics, or training signals for reinforcement learning.
- Design and run experiments that test whether interpretability-derived signals improve learning, exploration, generalization, robustness, or sample efficiency.
- Compare internally derived rewards against baselines such as human-generated verifiers, reward models, task-level outcome rewards, and standard intrinsic motivation methods.
- Use techniques such as probing, activation analysis, sparse autoencoders, causal interventions, feature attribution, or representation analysis to study model behavior.
- Analyze failure modes, including reward hacking, spurious features, non-causal correlations, objective misspecification, and overfitting to narrow evaluation distributions.
- Build research code, evaluation harnesses, and experimental infrastructure that make results reproducible and useful to the broader team.
- Communicate research progress clearly through written updates, internal presentations, and final project outputs.
Qualifications
- Currently enrolled in a PhD program in machine learning, computer science, artificial intelligence, computational neuroscience, mathematics, or a related technical field. Exceptional candidates with equivalent research experience may also be considered.
- Track record of research excellence or strong research promise, demonstrated through publications, preprints, open-source work, technical projects, competitions, or publicly available artifacts.
- Working understanding of reinforcement learning.
- Familiarity with mechanistic interpretability, representation analysis, or empirical methods for understanding neural networks.
- Strong programming ability in Python and experience with at least one major ML framework such as PyTorch or JAX.
- Clear written and verbal communication of technical ideas.
Skills
Required:Mechanistic interpretability methodsReinforcement learningPython programmingPyTorch or JAX
Last updated Jul 5, 2026. Interested? Apply on the company site.
About Vmax
Vmax is developing AI capable of open-ended learning. We build systems that exceed human performance across every domain, optimizing beyond the local maxima of learning from human expertise.
Vmax is automating reinforcement learning. We transform proprietary data and evals into new sets of environments. We refine agents on new examples of the tasks they are intended to perform.
AIagentsbessemer-ai-infrastructure-2026environmentsopen-ended learningreinforcement learningreinforcement-learning-platformsresearch
More open roles at Vmax
- Member of Technical Staff - Mechanistic Interpretability3mo agoSF · Research and Engineering
- Member of Technical Staff - RL Infrastructure3mo agoSF · Research and Engineering
- Member of Technical Staff - Applied RL3mo agoSF · Research and Engineering
- Research Fellowship - Open Endedness3mo agoSF · Research and Engineering
- Member of Technical Staff - RL Algorithms3mo agoSF · Research and Engineering