GrepJob
OpenAI

Agent Post-Training, Computer Use Research

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

Base Salary

$295k - $445k/yr

Responsibilities

  • Design and run experiments to improve agent behavior for complex computer use.
  • Own end-to-end improvements to the post-training stack, including RL and data pipelines.
  • Build evaluations and environments to identify model failures and create training data.
  • Collaborate with product teams to translate user needs into model improvements.
  • Work on early-training interventions that shape agent behavior.
  • Decide on integrations and capabilities for major model runs.
  • Enhance large-scale training machinery for reliability and efficiency.
  • Debug failures in models and develop concrete hypotheses for improvements.

Requirements

  • Strong technical fundamentals in machine learning, software engineering, or related fields.
  • Hands-on experience with LLMs, RL, and model training systems.
  • Ability to tackle open-ended problems with research and engineering skills.
  • Focus on product impact and model behavior beyond just benchmarks.
  • Capability to transition from vague problems to concrete experiments.
  • Comfortable working across various teams and communicating effectively.
  • Willingness to build systems and processes as needed by the team.

Categories

AI & MLBackendData Science