About idler
idler is a frontier data research lab. We build the evals and environments that the world's leading frontier labs use to measure and train their models.
After raising a $9m seed round led by Paradigm, we spent the last year developing coding evals for top coding models you know and love. At the same time, we've expanded into other domains besides coding: RSI & Auto-Research, Law, Enterprise Business, Cybersecurity, and others. Now, we are facing more lab demand for our data than we can serve, and are rapidly scaling the team to grow the business.
Our approach to creating training data scales using technology, and all of our data products are built on a unified self-reinforcing platform that learns through experience.
You would be joining a close-knit team that has reached product market fit, and your work would directly help to multiply our revenue.
You can see some of our work here: https://idler.ai/collections
About the role
As a Research Scientist at idler, you'll own measuring and improving how models learn from our tasks. The job is to maximize learning signal we produce per unit time. You'll draw on your own experience and collaborate with researchers at the frontier to validate our data quality, identify where improvements are needed, and create new datasets. To succeed, you'll need to have extensive experience doing this work in production at a frontier lab.
Examples of what you’ll do
Work with our customers — researchers at frontier labs — to design novel post-training recipes and data quality measurement techniques
Design and run our in-house post-training stack to measure model lift on our tasks
Develop new data products based on datasets and experts available to us
Identify opportunities to take advantage of self-reinforcing exponential feedback loops
Create agents to analyze thousands of environments and millions of trajectories
Help curate and specify task distributions for new corpora
Work with procurement to ensure external data we acquire is suitable for refinement
Create scaleable systems for ingesting & evaluating data we are considering buying
Develop new techniques for mining data for signal
What we’re looking for
1+ years of experience doing RL in production at a frontier lab
Track record of post-training an LLM end to end
Desire to drive the research roadmap and implementation on a fast-moving team
Deep curiosity about how machines learn from data and how to extract the maximum learning signal from our tasks
Tech stack
Typescript, React, NodeJS, Postgres, Redis, Vercel, Cursor/Claude Code/Codex, Tinker, Modal, AWS, Daytona, GRPO
Details
In-person in San Francisco
Competitive salary + meaningful equity
Free meals in office
Healthcare, 401(k), 15 days of PTO per year
Relocation assistance
Small, ambitious team
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.
Skills Required
- 1+ years of experience doing reinforcement learning in production at a frontier lab
- Track record of post-training a large language model end to end
- Ability and desire to drive the research roadmap and implementation on a fast-moving team
- Deep curiosity about how machines learn from data and how to extract maximum learning signal from tasks
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.
