Data & AI jobs

Research Fellowship - Mechanistic Interpretability

VmaxSan Francisco, CAHybridPhD or equivalent

Pay not listed

Looks real. 2 things to check before you apply.

On Vmax’s own careers site (Greenhouse), checked open today.

  • To check: Posted by the employer 6 months agoLong-open jobs are sometimes already filled. Ask when they plan to hire.
  • To check: No pay range listed, though one is likely required in CAAsk for the pay range before you interview. The law here likely requires one.
  • Checked: On the company's own careers siteGreenhouse board
  • Checked: Checked open todayGreenhouse board
  • Checked: No reposts foundGreenhouse board
  • Trust score 70 / 100 · Looks good
See all 6 checksShow fewer
How we check

What you’ll do

  • Develop interpretability methods to study representations, features, circuits, and computations in language models and agents.
  • Investigate using model internals to produce intrinsic rewards, auxiliary objectives, diagnostics, or reinforcement-learning training signals.
  • Design experiments comparing interpretability-derived signals with existing reward and intrinsic-motivation approaches.
  • Analyze failure modes and build reproducible research code, evaluation harnesses, and experimental infrastructure.

Summarised from the posting by AI and can be wrong. The full description is the source.

Requirements

Experience

  • Track record of research excellence or strong research promise, demonstrated through publications, preprints, open-source work, technical projects, competitions, or publicly available artifacts
  • Experience with LLM post-training methods (preferred)
  • Experience with scalable ML experimentation, distributed training, experiment tracking, or reproducible research infrastructure (preferred)

Education

  • Currently enrolled in a PhD program in machine learning, computer science, artificial intelligence, computational neuroscience, mathematics, or a related technical field, or equivalent research can be

Skills

  • 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
  • Familiarity with intrinsic motivation, unsupervised RL, auxiliary objectives, representation learning for RL, or curiosity-driven learning (preferred)

Other requirements

  • Role is based in the San Francisco office; hybrid arrangements may be considered for exceptional candidates
  • Interest in turning mechanistic understanding into practical training methods (preferred)

Your match

Sign in and add your resume to see which of this job's requirements it shows.

Sign in to check your match

Saved to your account, encrypted. The AI that reads it doesn't keep it or train on it.

Full job description

From Vmax’s careers site

About Vmax

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.

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.

Show full descriptionShow less

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.

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.

Role Requirements

  • 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.

Nice to have

  • 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.

Role specific location policy

  • This role is based in our San Francisco office; for exceptional candidates we are willing to consider a hybrid arrangement

Something wrong with this job? Report it · This flag looks wrong

Similar jobs

See more like this