Research Scientist

idler; San Francisco (CA); On-site; USD 150,000 - 210,000; Full time

Benefits offered by this job

Equity

Free meals in office

Healthcare

401(k)

15 days PTO

Relocation assistance

Job summary

idler is a frontier data research lab building the evals and environments that frontier labs use to measure and train models. As a Research Scientist at idler, you’ll own measuring how models learn from our tasks, validate data quality with researchers, and create new datasets.

This role is based in San Francisco, with collaboration across teams on post-training recipes, scalable data ingestion, and data refinement.

Qualifications

• 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

Responsibilities

• 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.
• Create scaleable systems for ingesting & evaluating data we are considering buying

Skills

RL in production

Post-training LLM

Data quality

Dataset design

Collaboration

Frontier lab experience

Curiosity

Tools

Typescript

React

NodeJS

Postgres

Redis

Vercel

Cursor

Job description

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.We closed on a multimillion-dollar contract with a top lab and raised a $9m seed round led by Paradigm. We are now facing more lab demand for our data than we can currently serve.Teaching AI superhuman capabilities is a responsibility we take very seriously. Our training data comes from work that is rigorous, ethically produced, and grounded in real expertise.

About the role

As a Research Scientist at idler, you'll own measuring and improving how models learn from our tasks. You'll draw on your own experience and collaborate with frontier researchers 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 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 usWork with procurement to ensure external data we acquire is suitable for refinementCreate scaleable systems for ingesting & evaluating data we are considering buying

What we’re looking for

• 1+ 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 tasks

Tech stack

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

DetailsIn-person in San FranciscoCompetitive salary + meaningful equityFree meals in officeHealthcare, 401(k), 15 days of PTO per yearRelocation assistanceSmall, ambitious team