RL Deep Learning Engineer

Tech Stack

Solid badges = required, outlined = preferred

Responsibilities

• Build and maintain the evaluation harness and RL environment infrastructure, including task runners, sandboxed environments, and scoring logic.
• Own the data pipeline for transforming freshly collected court filings into benchmark and RL tasks.
• Integrate with partner harnesses and model APIs for contamination-free evaluations.
• Collaborate with attorneys to translate legal workflows into structured, scorable task formats using the Harbor spec.
• Design and scale systems that convert millions of real court filings into verifiable evaluation environments and RL training tasks.

Soft Skills

Culture

Requirements