Research Fellowship - Mechanistic Interpretability

Vmax is an applied research lab developing AI capable of open-ended learning. The Research Fellowship focuses on mechanistic interpretability and reinforcement learning, with fellows owning focused research projects, conducting experiments, building reproducible research infrastructure, and contributing 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