Researcher, Alignment

OpenAI · San Francisco, United States · Full-time

Team: Research

Posted: 2024-08-27

Pay: USD 295000 – USD 500000 per year

The Alignment Researcher designs and implements experimental frameworks to ensure AI systems remain safe, trustworthy, and aligned with human intent as capabilities scale. The role involves developing scalable oversight methods, evaluating model robustness, and conducting research to understand the relationship between alignment and computational resources. Candidates must possess a PhD or equivalent research experience, strong engineering skills in large-scale machine learning, and proficiency in Python or TypeScript.

Skills & tags: ai alignment, machine learning, pytorch, python, typescript, research engineering, model evaluation, human-ai interaction, computational science, data science

View and apply at the original posting

Postings belong to their employers; this page links to the source.

JOB DETAILS

Job details