Software Engineer

Idler; San Francisco (CA); On-site; USD 120,000 - 180,000; Full time

Benefits offered by this job

Healthcare coverage

401(k)

15 days PTO

Meals, coffee, and snacks

Relocation assistance

Team offsites and events

Latest MacBook Pro

Job summary

Idler is building reinforcement learning environments in San Francisco and is rapidly scaling the team to meet demand. You will develop UI components and backend services for environment generation and validation, collaborating with senior engineers and researchers to ensure the environments are technically robust and fair.

You'll work with a modern stack including Typescript, React, NodeJS, Postgres, Redis, Vercel, Cursor, and you will help ship features quickly while iterating on feedback from

Responsibilities

• Build UI components and backend services for environment generation and validation.
• Implement automated testing and QA workflows.
• Work with real codebases to understand what makes effective training data.
• Ship features quickly and iterate based on feedback from AI researchers at leading labs

Skills

UI development

Backend services

Automated testing

QA workflows

Codebase understanding

Tools

Typescript

React

NodeJS

Postgres

Redis

Vercel

Cursor

Job description

What we do

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 do

Build features and tooling for our agentic systems that create and QA coding environments. You'll work alongside senior engineers and the founding team, learning how to design systems that are both technically sound and philosophically robust. A big part of our work is thinking critically about what makes a coding environment "good" and "fair".

Concretely, you'll:

• Build UI components and backend services for environment generation and validation

• Implement automated testing and QA workflows

• Work with real codebases to understand what makes effective training data

• Ship features quickly and iterate based on feedback from AI researchers at leading labs

You'll work with

The founding team, a founding engineer, and a small group of engineers (we're hiring quickly). You'll learn directly from people building at the cutting edge of AI training.

Tech stack

Typescript, React, NodeJS, Postgres, Redis, Vercel, Cursor

Benefits

• Healthcare 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.