Software Engineer

The role

You will design, build, and quality-assure RL tasks. You will own the full lifecycle of tasks including ideation, grading infrastructure, running models, failure analysis, and iteration.

What you will do

• Design, build, and quality-assure RL tasks
• Own the full lifecycle of tasks including ideation, grading infrastructure, and failure analysis
• Run frontier models against tasks
• Use coding agents heavily to direct them and evaluate their output
• Contribute to shared infrastructure such as build pipelines, QA automation, or tooling

Required qualifications

• Can code in Python
• Are confident working independently at a consistent pace
• Have developed an intuition for what coding agents can and can't do

Benefits

• health
• dental
• vision
• life insurance

About the company

Mechanize builds reinforcement learning environments that frontier AI labs use to train and evaluate their coding models. It is a ~20 person team in San Francisco.