GrepJob
OpenAI

Agent Post-Training, Frontier Evals and Environments Research

OpenAI
Apply
about 3 hours ago
San Francisco, CA, USAMid Level / Senior
H1B Sponsor

Base Salary

$295k - $445k/yr

Responsibilities

  • Create ambitious reinforcement learning environments to evaluate model capabilities.
  • Develop methodologies for automatic exploration of model behavior.
  • Analyze the scalability, reliability, and variance of evaluation methods.
  • Steer training for major model runs and observe advancements firsthand.
  • Design systems for continuous evaluation and improvement.
  • Build self-improvement loops for enhanced model understanding.

Requirements

  • Strong technical fundamentals in machine learning, software engineering, or related fields.
  • Hands-on experience with LLMs, reinforcement learning, and model training.
  • Ability to navigate open-ended problems with unclear paths and noisy signals.
  • Focus on product impact and model behavior beyond just benchmarks.
  • Capability to transition from vague problems to concrete experimental designs.
  • Excellent communication skills across research, product, and safety teams.

Categories

AI & MLData ScienceTesting