- Experience
- Fresher welcome
- Pay
- $300K per year
- Education
- Not specified
- Location
- San Francisco, United States
- Work mode
- On-site
- Job type
- Full-time
About this role
Mechanize builds reinforcement learning environments that frontier AI labs use to train and evaluate coding models. Junior engineers design, build, and refine self-contained software-engineering RL tasks that expose model failures and drive improvement.
What you will do
- Design, build, and refine RL tasks with prompt, environment, and automated grader
- Own full lifecycle: idea → grading infrastructure → model evaluation → analysis → iteration
- Direct coding agents, evaluate their output, and detect subtle failures
- Anticipate model shortcuts and distinguish capability gaps from grader issues
What the employer expects
- Strong technical fundamentals combined with intuition for AI model behavior
- Just graduated or about to graduate
- Experience working heavily with coding agents is a strong plus
Benefits
- Offers Equity
- Offers Bonus
Skills
- coding agents
- RL environments
- frontier model evaluation
Apply on the employer's site
The application opens on Ashby. Dev Portal Notes does not collect your application or charge a fee.
Know someone who fits this role?
Applications are handled on the employer's own site.
Close the skill gap
Some links on this page may generate a small commission at no extra cost to you.