Research Scientist

About idleridler 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/collectionsAbout the roleAs 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 doWork with our customers — researchers at frontier labs — to design novel post-training recipes and data quality measurement techniquesDesign and run our in-house post-training stack to measure model lift on our tasksDevelop new data products based on datasets and experts available to usIdentify opportunities to take advantage of self-reinforcing exponential feedback loopsCreate agents to analyze thousands of environments and millions of trajectoriesHelp curate and specify task distributions for new corporaWork with procurement to ensure external data we acquire is suitable for refinementCreate scaleable systems for ingesting & evaluating data we are considering buyingDevelop new techniques for mining data for signalWhat we’re looking for1+ years of experience doing RL in production at a frontier labTrack record of post-training an LLM end to endDesire to drive the research roadmap and implementation on a fast-moving teamDeep curiosity about how machines learn from data and how to extract the maximum learning signal from our tasksTech stackTypescript, React, NodeJS, Postgres, Redis, Vercel, Cursor/Claude Code/Codex, Tinker, Modal, AWS, Daytona, GRPODetailsIn-person in San FranciscoCompetitive salary + meaningful equityFree meals in officeHealthcare, 401(k), 15 days of PTO per yearRelocation assistanceSmall, ambitious teamThis 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.