ApplyBlast uses AI to match you with the right jobs, tailor your resume and cover letter, and apply automatically so you can land your dream job faster.

Features

Auto Apply Resume Optimizer Cover Letter Optimizer Interview Prep

Company

Social Media

Need Help?

team@applyblast.com

Agent Post-Training, Context Research at OpenAI - ApplyBlast

Agent Post-Training, Context Research

OpenAI

3 months ago

4.5 on Glassdoor

Remote

Full Time

Senior

6 applicants

View Job Listing

Apply to 100+ jobs

About this role

As a Context Researcher on OpenAI's Agent Post-Training team, you will scale compute spent on context to enable the next generation of AI agents like Codex and ChatGPT. You will design experiments, build end-to-end improvements to the post-training stack, and partner with product and infrastructure teams to ship model improvements that enhance reliability and utility.

Responsibilities

Design and run experiments to improve compute scaling on context
Build end-to-end improvements to the post-training stack including RL and graders
Develop evals and environments to expose model failures and inform training
Partner with product teams to translate user needs into model improvements
Debug hard failures in shipped models and turn qualitative behavior into concrete fixes

Skills

About OpenAI

openai.com

Headquarters

San Francisco, California, United States

Company Size

201-500 employees

Founded

2015

View Profile

OpenAI is an AI research and deployment company that develops advanced artificial intelligence models and products, including ChatGPT and APIs, to help people and organizations solve problems, create content, and build intelligent applications.