Idler builds reinforcement learning environments that teach AI models to code like 0.01% engineers. Our training environments are based on real-world coding scenarios that frontier models will actually encounter.
We've closed a multimillion-dollar contract with a leading foundation lab (the largest they've issued to date). Demand is outpacing our capacity to deliver, so we're scaling the team fast.
What you'll doBuild agentic systems that create and QA coding environments at scale. Most of your day will be spent designing these systems to be extremely sound. A big part of our work is thinking critically about what makes a coding environment and task "good" and "fair". This requires high agency and philosophical thinking alongside technical execution.
Concretely, you'll:
Design and build scaleable systems that generate RL environments
Create automated QA systems to validate environment quality and fairness
Work directly with AI researchers at leading labs to understand what makes training data effective
Support new product lines as we expand beyond coding environments
Lead the process of identifying, specifying, and implementing core technology primitives that maximize the leverage of the rest of the team.
Understand and own the technology stack end-to-end.
8+ years of professional software engineering experience.
Lead and mentor more junior members of the team.
The founding team, a founding engineer, and a small group of engineers (we're hiring quickly). You'll have direct access to AI researchers at frontier labs.
Tech stackTypescript, React, NodeJS, Postgres, Redis, Vercel, Cursor
BenefitsHealthcare coverage, 401(k), and 15 days PTO.
Meals, coffee, and snacks (that you will actually enjoy) covered during working days.
Latest MacBook Pro and equipment.
Relocation assistance available.
Team offsites and events (we love hanging out).
This is an in-person role in San Francisco. We're a tight-knit founding team and we play to win. Join us if you like to win too.
Top Skills
What We Do
Idler builds reinforcement learning environments that teach AI models to code at expert human levels. We create training environments based on real-world coding scenarios that prepare models for the complex challenges they'll face in production.
Why Work With Us
You'll be joining a team that's expanding quickly, get direct access to AI researchers at frontier labs, and be put in a position to grow as fast as you can handle.
Gallery
Idler Offices
OnSite Workspace
All employees work in person out of our office in the Dogpatch neighborhood of San Francisco.
