Staff AI Researcher — RL & Security

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

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.