RL Deep Learning Engineer
Core
Building reinforcement learning environments, evaluation harnesses, and benchmark systems for long-horizon legal reasoning tasks to power AI labs and enterprise legal workflows.
Role type
Senior IC reinforcement learning infrastructure engineer
Builds
RL environments, evaluation harnesses, task runners, scoring systems, and sandboxed execution environments for legal AI
Domain
Legal technology + Reinforcement Learning infrastructure
Deliverable
production ML models | infrastructure
Required skills
Python engineering, backend systems design, large-scale data processing, systems thinking, debugging, product ownership, autonomous IC operation, AI coding tools usage
Preferred skills
TypeScript, startup founding experience, RL environment construction, LLM evaluation frameworks, scalable Python backend development, messy dataset handling
Technologies
Python, TypeScript, Cursor, Claude Code, Codex
Responsibilities
Build and maintain RL environment infrastructure for long-horizon legal reasoning tasks; Design scalable evaluation harnesses and scoring systems; Convert raw legal filings into benchmark and RL training tasks; Develop contamination-free evaluation pipelines; Integrate with partner model APIs; Collaborate with attorneys to translate legal workflows into structured tasks; Build scalable data pipelines for legal reasoning environments; Write production-quality Python systems; Contribute to infrastructure supporting thousands of concurrent agent evaluations
Seniority
Senior, hands-on IC