Junior Reinforcement Learning Engineer

Mechanize; Oakland, San Francisco (CA, CA); On-site; USD 90,000 - 150,000; Full time

Benefits offered by this job

Health insurance

Dental insurance

Vision insurance

Life insurance

Job summary

Mechanize builds reinforcement learning environments that frontier AI labs use to train and evaluate coding models. You will design, build, and refine RL tasks, owning the full lifecycle from idea to grading infrastructure and iteration.

Strong technical fundamentals and an intuition for AI model behavior are needed: anticipate shortcuts, distinguish grader issues from capability gaps, and understand how prompts are interpreted.

Qualifications

• Strong technical fundamentals and intuition for AI model behavior.
• Anticipate where a model will take shortcuts and distinguish gaps from grader issues.
• Understand how a model will interpret prompts and evaluations.

Responsibilities

• Design, build, and refine RL tasks with a prompt, an environment, and an automated grader; own the full lifecycle.
• Direct coding agents, evaluate their outputs, and know when they fail in subtle ways.

Skills

Python

Autonomous work

Creative problem solving

Education

Bachelor's degree in Computer Science or related field

Tools

Git

Job description

Mechanize builds reinforcement learning environments that frontier AI labs use to train and evaluate coding models. You will design, build, and refine RL tasks, owning the full lifecycle from idea to grading infrastructure and iteration.

Strong technical fundamentals and an intuition for AI model behavior are needed: anticipate shortcuts, distinguish grader issues from capability gaps, and understand how prompts are interpreted.