← All roles

Member of Technical Staff - RL Algorithms

Vmax· Research and Engineering
Apply on company site
SF$300k - $500kFull-timePosted 3mo ago

About the role

RL-focused researcher role at Vmax, combining pre-LLM and post-LLM learning to improve sample efficiency and reliability of RL for language models and agentic systems.

Responsibilities

  • Develop new RL algorithms for post-training language models.
  • Adapt ideas from pre-LLM reinforcement learning to modern LLM and agentic settings (e.g., model-based RL, temporal abstraction, value-based learning).
  • Establish empirical baselines and evaluation protocols for sample efficiency, robustness, generalization, and reward exploitation in LLM RL.
  • Analyze failure modes of RL-trained models (reward hacking, mode collapse, over-optimization, exploration failures, distribution shift).
  • Collaborate with researchers on environments, evals, interpretability, reward modeling, and infrastructure to build reliable training systems.
  • Own and develop a research agenda within Vmax, from identifying directions to executing experiments and communicating results.

Qualifications

  • PhD or equivalent experience in machine learning, reinforcement learning, or closely related field.
  • Track record of research excellence (publications, open source, deployed AI systems, or other technical contributions).
  • Deep understanding of modern ML, especially RL, representation learning, and large language models.
  • Strong familiarity with LLM post-training methods.
  • Experience designing and running rigorous ML experiments (ablations, baselines, evaluation design, failure analysis).
  • Experience with large-scale ML infrastructure, distributed training, experiment tracking, data pipelines, debugging unstable training runs.
  • Expertise with Python and at least one major ML framework (PyTorch or JAX).
  • Ability to work independently on open-ended research problems and translate ideas into concrete experiments.

Skills

Required:Reinforcement learningLLM post-training methodsExperiment design and analysisPythonPyTorch or JAX
Last updated Jul 5, 2026. Interested? Apply on the company site.
Vmax logo

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
Company profileWebsite

More open roles at Vmax