Frontier RL Research Scientist - Drive Model Learning

Idler; San Francisco, Northern (CA, KY); Hybrid; USD 150,000 - 230,000; Full time

Benefits offered by this job

Free meals in office

Healthcare

401(k)

15 days PTO per year

Relocation assistance

Equity

Job summary

Idler, a frontier data research lab in San Francisco, seeks a Research Scientist to measure and improve how models learn from our tasks. You will maximize the learning signal per unit time and validate data quality through production-scale experiments with frontier researchers.

Responsibilities include designing post-training recipes, running our in-house evaluation stack, developing data products, and building scalable data-ingest and evaluation pipelines.

Qualifications

• 1+ year of RL experience in production at a frontier lab.
• Track record of post-training an LLM end-to-end.
• Desire to drive the research roadmap on a fast-moving team.
• Deep curiosity about how machines learn from data and how to maximize learning signals.

Responsibilities

• Design novel post-training recipes and data quality measurement techniques with customers.
• Design and run in-house post-training stack to measure model lift on tasks.
• Develop data products based on datasets and experts available to us.
• Create scalable systems for ingesting and evaluating data.
• Identify opportunities to leverage self-reinforcing feedback loops.

Skills

Reinforcement learning

LLM post-training

Research roadmap

Data quality

Problem solving

Tools

Typescript

React

NodeJS

Postgres

Redis

Job description

Idler, a frontier data research lab in San Francisco, seeks a Research Scientist to measure and improve how models learn from our tasks. You will maximize the learning signal per unit time and validate data quality through production-scale experiments with frontier researchers.

Responsibilities include designing post-training recipes, running our in-house evaluation stack, developing data products, and building scalable data-ingest and evaluation pipelines.