🛠 Tech Stack

💼 About This Role

You'll join the Interpretability team at OpenAI, studying internal representations of deep learning models to ensure safe AGI. Your research will directly impact model safety through mechanistic interpretability techniques. You'll collaborate on large-scale AI systems with unique resources.

🎯 What You'll Do

• Develop and publish research on understanding deep network representations.
• Engineer infrastructure for studying model internals at scale.
• Collaborate across teams on unique OpenAI projects.
• Guide research directions toward long-term scalability.

📋 Requirements

• PhD or research experience in CS/ML or related field.
• 2+ years of research engineering experience.
• Proficiency in Python or similar languages.

✨ Nice to Have

• Experience in AI safety or mechanistic interpretability.
• Deep curiosity and enthusiasm for long-term AI safety.

🎁 Benefits & Perks

• 💰 Competitive equity package
• 🏖️ Flexible hybrid work
• 🧠 Access to large-scale AI systems