Research Fellow
Vmax
Research Fellow
Vmax
Automates generation of reinforcement learning environments
Vmax is an applied research lab developing AI capable of open-ended learning. We are building systems to exceed humans in all capacities by optimizing beyond the local maxima of learning from human expertise.
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.
This 3 to 6 month fellowship is for PhD students or equivalent early-career researchers who want to work at the intersection of mechanistic interpretability and reinforcement learning. You will own a focused research project, work closely with Vmax technical staff, and contribute to research publications.
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.
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.
Experience with LLM post-training methods
Familiarity with intrinsic motivation, unsupervised RL, auxiliary objectives, representation learning for RL, or curiosity-driven learning.
Experience with scalable ML experimentation, distributed training, experiment tracking, or reproducible research infrastructure.
Interest in turning mechanistic understanding into practical training methods, rather than only analyzing models after training.
This role is based in our San Francisco office; for exceptional candidates we are willing to consider a hybrid arrangement
Vmax.ai builds tools to automate reinforcement learning (RL) development. It creates scalable RL environments from proprietary data so engineers can train agents for long-horizon tasks without a lot of manual RL engineering. The core product concept is to automatically transform company data and evaluation metrics into reusable RL environments, enabling post-training of large language model–based agents for domain-specific use cases. The company distinguishes itself by combining automated environment design with data-driven RL environment generation, aiming to cut human intervention in RL workflows. The founding team’s deep RL background, stealth mode status, and backing from South Park Commons position it to pursue enterprise-grade RL automation and domain-specific AI through a platform that handles data-to-environment conversion and subsequent agent fine-tuning. Its goal is to scale RL development by reducing setup work and enabling long-horizon tasks across domains.
Explore more opportunities at Vmax