Job · Anthropic

Research Engineer, Code RL (Reinforcement Learning)

Build coding tasks, RL environments and verifiers, then run training experiments and investigate model improvement.

Needs a fresh check

San Francisco, CA or New York City, NY

Application deadline: Not stated

USD 500,000–850,000/year (salary; 2026-10-05). Published annual salary range; employer determines level.

This record is historical or needs another check. It is excluded from verified-open recommendations. Read the institution’s current source before applying.

What the institution asks for

Strong Python, concurrent programming and software engineering; rigorous experimental design and interpretation.
RL, evaluation harnesses and distributed training are additional strengths. Bachelor’s degree or equivalent; office attendance expected.

ProfRod’s suggested preparation

Understand what this work involves

Practice the experimental design and interpretation used to evaluate coding and RL experiments.

Did model A really beat model B?

Write a paired-comparison memo

Predict the difference before recomputing the saved results. Name the sampling unit, interval and one limit; keep the notebook output with your memo.

Continue the exercise

Keep it on your desk

Your free account saves this entry. Saving does not apply to the institution or subscribe you to alerts.