
Idler
San Francisco, CA
Reinforcement learning environments for AI coding training
About
Idler builds reinforcement learning environments that teach AI models to code at expert human levels. They create training environments based on real-world coding scenarios to prepare models for production challenges. This enables frontier AI labs to train more capable coding agents.
Tech stack
TypeScript, React, Node.js, Postgres, Redis, Vercel
Perks & benefits
Health insurance, 401k, Free lunch, Relocation assistance
More AI companies
AI companiesSan Francisco, CA
San Francisco, CA
San Francisco, CA
Berkeley, CA
San Francisco, CA
Seattle, WA
Open jobs
5Own the recruitment, operations, and tooling that connect a network of experts to data-production projects. The role suits resourceful operators with 1–4 years of experience, strong communication skills, and the ability to build lightweight tools independently.
Research Scientist responsible for measuring and improving how frontier models learn from tasks, designing post-training experiments, validating data quality, and creating datasets and evaluation systems. Requires production reinforcement-learning experience at a frontier lab and end-to-end LLM post-training experience.
Design Engineer responsible for shaping the user experience and building performant full-stack applications for complex reinforcement-learning environments. The role requires product experience, strong React/TypeScript/Node.js skills, design judgment, and rapid user-driven iteration.
Own customer-facing technical delivery for AI labs and partner organizations, translating real-world workflows into reusable evaluation and reinforcement-learning infrastructure. The role requires strong production engineering, communication, judgment, and ownership in an ambiguous, fast-paced environment.
Build UI components, backend services, and QA workflows for reinforcement learning environments that train AI models to code. Work with TypeScript, React, Node.js stack alongside founding team in fast-scaling AI startup.