Vmax
Automates generation of reinforcement learning environments
Member of Technical Staff - Open Endedness
SF office; hybrid arrangement possible for exceptional candidates.
About the job
- PhD or equivalent experience in machine learning, reinforcement learning, artificial intelligence, or a closely related field.
- Track record of strong technical work, demonstrated through publications, open-source projects, deployed systems, competitions, or equivalent contributions.
- Deep understanding of reinforcement learning
- Strong interest in open-ended learning
- Experience with LLM post-training
- Strong empirical research ability, including designing experiments, choosing meaningful baselines, running ablations, and diagnosing unexpected results.
- Strong programming ability in Python and experience with at least one major ML framework such as PyTorch or JAX.
- Ability to work independently on ambiguous research problems and turn high-level ideas into concrete experimental programs.
- Ability to collaborate effectively with researchers and engineers on ambiguous, fast-moving technical problems.
- Clear written and verbal communication of technical ideas, results, tradeoffs, and risks.
- Develop RL methods for agents that can discover useful objectives, tasks and curricula without relying entirely on human-specified rewards.
- Design systems for open-ended learning, including unsupervised/automated environment design, asymmetric self-play, and intrinsic motivation.
- Build training loops where agents learn from interaction, exploration, novelty, competence progress, self-generated challenges, or other nonstandard reward signals.
- Investigate how agents can avoid collapse into trivial, degenerate, or easily exploitable objectives.
- Own and develop a research agenda within Vmax, from identifying promising directions to executing experiments and communicating results.
- Experience with open-ended learning, automatic curriculum generation, intrinsic motivation, self-play, goal-conditioned RL, unsupervised skill discovery, multi-agent RL, quality-diversity, or evolutionary methods.
- Familiarity with methods such as POET, population-based training, or multi-agent RL
- Experience designing benchmarks or evals for generalization, exploration, long-horizon learning or behavioral diversity
- Demonstrated taste for identifying non-obvious research directions and converting them into tractable experiments.
About the company
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.
Company Size
11-50
Company Stage
N/A
Total Funding
N/A
Headquarters
San Francisco, California
Founded
2025
Get referred to Vmax
See people who can refer or advise you
Simplify's Take
What believers are saying
- South Park Commons still lists Vmax active and hiring in August 2026.
- Vmax published unix-ctf and PROPEL in 2026, proving real research velocity.
- Hiring for RL Infrastructure and Applied RL suggests customer-ready systems work, not just theory.
What critics are saying
- Open-ended learning remains unproven commercially; research outputs do not equal a durable product.
- $300k-$500k roles in 2026 signal heavy burn before revenue arrives.
- OpenAI, Anthropic, and Nvidia can commoditize RL environment tooling, killing Vmax's moat.
What makes Vmax unique
- Vmax builds proprietary-data-to-RL-environment pipelines, not generic model fine-tuning.
- Its unix-ctf and PROPEL research show environment generation for long-horizon agents.
- Matthew Sargent and Augustine Mavor-Parker bring PhD-level RL depth from UCL, Redwood, and Illumina.
Help us improve and share your feedback! Did you find this helpful?