RefolkCandidates
JobsBuild my resume

Researcher, Pretraining Safety

OpenAI · San Francisco

$295k - $445k/yrMid levelScience and researchSafety SystemsSafety SystemsPosted 9 months ago
Apply with a tailored resumeView the original posting

About this role

ABOUT THE TEAM The Safety Systems team https://openai.com/safety/safety-systems is responsible for various safety work to ensure our best models can be safely deployed to the real world to benefit the society and is at the forefront of OpenAI's mission to build and deploy safe AGI, driving our commitment to AI safety and fostering a culture of trust and transparency. The Pretraining Safety team’s goal is to build safer, more capable base models and enable earlier, more reliable safety evaluation during training. We aim to: 1. Develop upstream safety evaluations that to monitor how and when unsafe behaviors and goals emerge; 2. Create safer priors through targeted pretraining and mid-training interventions that make downstream alignment more effective and efficient 3. Design safe-by-design architectures that allow for more controllability of model capabilities In addition, we will conduct the foundational research necessary for understanding how behaviors emerge, generalize, and can be reliably measured throughout training. ABOUT THE ROLE The Pretraining Safety team is pioneering how safety is built into models before they reach post-training and deployment. In this role, you will work throughout the full stack of model development with a focus on pre-training: - Identify safety-relevant behaviors as they first emerge in base models - Evaluate and reduce risk without waiting for full-scale training runs - Design architectures and training setups that make safer behavior the default - Strengthen models by incorporating richer, earlier safety signals We collaborate across OpenAI’s safety ecosystem - from Safety Systems to Training - to ensure that safety foundations are robust, scalable, and grounded in real-world risks. IN THIS ROLE, YOU WILL: - Develop new techniques to predict, measure, and evaluate unsafe behavior in early-stage models - Design data curation strategies that improve pretraining priors and reduce downstream risk - Explore safe-by-design architectures

Excerpt from the posting OpenAI published. Read the full description on their site before applying.

Skills this posting mentions

Full Stack DevelopmentResearchArtificial Intelligence

About OpenAI

OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity. AI is an extremely powerful tool that must be created with safety and human needs at its core. OpenAI is dedicated to putting that alignment of interests first - ahead of profit. To achieve our mission, we must encompass and value the many different perspectives, voices, and experiences that form the full spectrum of humanity. Our investment in diversity, equity, and inclusion is ongoing, executed through a wide range of initiatives, and championed and supported by leadership. At OpenAI, we believe artificial intelligence has the potential to help people solve immense global challenges, and we want the upside of AI to be widely shared. Join us in shaping the future of technology.

All 754 openings at OpenAI

Apply to this role, tailored

Queue Researcher, Pretraining Safety at OpenAI and I will read the posting, rewrite your resume against it, draft the cover letter, and score the fit before you send anything.

Applications finish as drafts. Nothing is sent until you read it and press send. New accounts start with 500 free credits.

Tailor my applicationHow it works

More roles at OpenAI

See all

Similar roles elsewhere

See more

Listed from the job board OpenAI publishes. Refolk is not the employer and does not handle their hiring. Applications go to OpenAI directly.