Research Engineer / Scientist, Pretraining Safety

Details

About the Team

The Safety Systems team is responsible for various safety work to ensure our best models can be safely deployed to the real world to benefit society. The Pretraining Safety team’s goal is to build safer, more capable base models and enable earlier, more reliable safety evaluation during training. Key aims include:

• Develop upstream safety evaluations to monitor how and when unsafe behaviors and goals emerge
• Create safer priors through targeted pretraining and mid-training interventions that make downstream alignment more effective and efficient
• Design safe-by-design architectures that allow for more controllability of model capabilities

The team conducts foundational research necessary for understanding how behaviors emerge, generalize, and can be reliably measured throughout training.

About the Role

You will work throughout the full stack of model development with a focus on pre-training. Specific focuses include:

• Identifying safety-relevant behaviors as they first emerge in base models
• Evaluating and reducing risk without waiting for full-scale training runs
• Designing architectures and training setups that make safer behavior the default
• Strengthening models by incorporating richer, earlier safety signals

You will collaborate across OpenAI’s safety ecosystem — from Safety Systems to Training — to ensure safety foundations are robust, scalable, and grounded in real-world risks.

Responsibilities

• 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 and training configurations that improve controllability
• Introduce novel safety-oriented loss functions, metrics, and evaluations into the pretraining stack
• Work closely with cross-functional safety teams to unify pre- and post-training risk reduction

Requirements / Qualifications

You might thrive in this role if you:

• Have experience developing or scaling pretraining architectures (LLMs, diffusion models, multimodal models, etc.)
• Are comfortable working with training infrastructure, data pipelines, and evaluation frameworks (e.g., Python, PyTorch/JAX, Apache Beam)
• Enjoy hands-on research — designing, implementing, and iterating on experiments
• Enjoy collaborating with diverse technical and cross-functional partners (e.g., policy, legal, training)
• Are data-driven with strong statistical reasoning and rigor in experimental design
• Value building clean, scalable research workflows and streamlining processes for yourself and others

Compensation & Benefits

• Base salary range: $310,000 – $460,000 (base pay may vary depending on market location, knowledge, skills, and experience)
• Offers equity and may include performance-related bonus(es) for eligible employees
• Medical, dental, and vision insurance with employer HSA contributions
• Pre-tax accounts for Health FSA, Dependent Care FSA, and commuter expenses
• 401(k) with employer match
• Paid parental leave, paid medical and caregiver leave
• Paid time off: flexible PTO for exempt employees and up to 15 days annually for non-exempt employees
• 13+ paid company holidays and office closures, plus paid sick/safe time as required by law
• Mental health and wellness support; employer-paid basic life and disability coverage
• Annual learning and development stipend
• Daily meals in offices and meal delivery credits as eligible
• Relocation support for eligible employees
• Additional taxable fringe benefits such as charitable donation matching and wellness stipends

Additional Notes

• Background checks will be administered in accordance with applicable law.
• OpenAI is an equal opportunity employer and is committed to reasonable accommodations for applicants with disabilities.