Researcher, Alignment Training

OpenAI

San Francisco, California, United States
Senior researcher with technical depth
Experience in large-scale model training
Expertise in synthetic data generation
The Alignment Training team studies how frontier models acquire durable behavioral tendencies across the training stack

Job Summary

  • The Alignment Training team studies how frontier models acquire durable behavioral tendencies across the training stack.
  • You will help shape the research agenda by defining desired behaviors and designing data interventions to teach them.
  • The role requires moving from ambiguous behavioral questions to concrete experimental programs that distinguish durable learning from artifacts.

Matching Summary

The Alignment Training team studies how frontier models acquire durable behavioral tendencies across the training stack.

Skills & Requirements

Must-have

  • Senior researcher with technical depth
  • Experience in large-scale model training
  • Expertise in synthetic data generation
  • Strong background in model evaluation
  • Ability to design experimental programs

Nice-to-have

  • Interest in alignment problems
  • Excellent judgment on research questions
  • Clear communication across teams
  • Preference for evidence-driven work

Key Requirements

  • Senior researcher level experience
  • Exceptional technical depth in ML
  • Proven record in pre/post-training or synthetic data

Work Rights

Not specified

Tailored Resume

Cover Letter