Alignment Research Engineer

OpenAI is looking for an Alignment Research Engineer to join our Superalignment team. You will work on developing scalable oversight techniques, automated red-teaming, and interpretability methods for frontier AI systems. This is a high-impact role where your work directly contributes to ensuring that advanced AI systems remain safe and beneficial. You will collaborate with world-class researchers on some of the most important problems in AI. The ideal candidate has strong ML engineering skills, a passion for safety research, and the ability to rapidly prototype and evaluate new alignment techniques.

- 5+ years of ML engineering or research experience - Experience with RLHF and related training methods - Strong Python, PyTorch, and distributed training skills - Familiarity with interpretability and mechanistic understanding of models - PhD or equivalent research experience - Published work in AI safety, alignment, or related fields preferred