Safety Training Researcher – Post-Training & RLHF Specialist

OpenAI is seeking researchers to advance safety training for its models. You will develop methods to improve model behavior after pretraining, including RLHF, RLAIF, DPO, PPO, and reward modeling.

This role is highly cross-functional. You will collaborate with core training teams, product, policy, legal, trust and safety, and domain experts to identify risks, design interventions, and deploy safety improvements in OpenAI products.

#J-18808-Ljbffr…