Member of Technical Staff - AI Researcher, Reinforcement Learning

Enclosure; San Francisco (CA); On-site; USD 180,000 - 250,000; Full time

Benefits offered by this job

Competitive compensation package

Ownership over research direction

Close collaboration with frontier AI"

Job summary

Enclosure is hiring an exceptional RL researcher. You'll own a significant part of our RL research as an IC, where exploration, curiosity, and grit outweigh degrees. You’ll contribute across RL research, tooling, and system-building in a frontier AI security context.

The role emphasizes large-scale RL, language-model work, and agent systems with strong ML fundamentals, collaborating across training, data, evals, and infrastructure to ship robust research outcomes.

Qualifications

• Experience with large-scale RL or post-training for language models, esp. RLVR, policy optimization, or outcome-based RL.
• Ability to design verifiable tasks, environments, graders, reward functions, or curricula for long-horizon tasks.
• Experience training/evaluating tool-using, coding, or multi-agent systems, incl. agent harness design.
• Strong experimental judgment, including transfer evaluation and diagnosing reward hacking.
• Solid ML and software engineering fundamentals across training, data, evals, infrastructure, and product.

Skills

RL research

RL & LM Research

Task design

Agent harness design

Experimental judgment

ML fundamentals

Software engineering

Python

PyTorch

Tools

Python

PyTorch

Job description

About Enclosure

Enclosure is the world’s first superintelligence security lab focused on preventing the sabotage, escape, and theft of ASI. We are building ASI-grade security for model weights, and nation-state-grade security for data centers.

We’re backed by leaders across OpenAI, Anthropic, Google DeepMind, SpaceXAI, CoreWeave, NVIDIA, other frontier AI labs, and the national security community (including former NSA and intelligence community leadership). We are frontier AI, cybersecurity, quantum security, and national security researchers.

About the Role

Enclosure is hiring an exceptional RL researcher. You'll own a significant part of our RLresearch as an IC. We care less about degrees and more about a track record of exploration, curiosity, and grit.

Requirements

This role requires deep experience in multiple of the following areas:

• Experience with large-scale RL or post-training for language models, especially RLVR, policy optimization, or outcome-based reinforcement learning

• Experience designing verifiable tasks, environments, graders, reward functions, or curricula for agentic, coding, cyber, or other long-horizon tasks

• Experience training and evaluating tool-using, coding, or multi-agent systems, including agent harness design

• Strong experimental judgment, including evaluating transfer, diagnosing reward hacking or specification gaming, and iterating from noisy results

• Strong ML and software engineering fundamentals, with the ability to work across training, data, evals, infrastructure, and product

What Sets You Apart

We're especially excited if you:

• Demonstrate strong engineering judgment in the systems you've built

• Get excited by hard problems and the challenge of figuring them out

• Are highly adaptive and comfortable with how quickly the frontier shifts

• Have evidence of self-directed technical work, such as open-source contributions, technical writing, tools, packages, or public projects with strong systems thinking

• Communicate with clarity and directness

• Bring a humble, low-ego attitude and care deeply about helping the team win

Why Join

Enclosure is securing the path to superintelligence.

What we offer:

• Competitive compensation package

• Ownership over research direction

• Close collaboration with frontier AI security and infrastructure teams