OpenAI's Safety Systems team is responsible for ensuring their AI models can be safely deployed to the real world. The Pretraining Safety team's goal is to build safer, more capable base models and enable earlier, more reliable safety evaluation during training.
Requirements
- 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
- 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
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 evals into the pretraining stack
- Work closely with cross-functional safety teams to unify pre- and post-training risk reduction
- Identify safety-relevant behaviors as they first emerge in base models
- Evaluate and reduce risk without waiting for full-scale training runs
Other
- Enjoy collaborating with diverse technical and cross-functional partners (e.g., policy, legal, training)
- We are an equal opportunity employer, and we do not discriminate on the basis of race, religion, color, national origin, sex, sexual orientation, age, veteran status, disability, genetic information, or other applicable legally protected characteristic.
