💼 About This Role

You'll conduct state-of-the-art research on AI safety topics such as RLHF and adversarial training for OpenAI's core model training. Your work will directly launch safety improvements in OpenAI's products. You'll set research directions and collaborate with cross-functional teams to ensure the highest safety standards.

🎯 What You'll Do

• Conduct research on AI safety topics like RLHF and adversarial training
• Implement new methods in core model training and product safety
• Set research directions for safer, aligned, robust AI systems
• Collaborate with cross-functional teams on safety standards

📋 Requirements

• 4+ years of experience in AI safety research
• PhD in computer science, machine learning, or related field
• Experience with RLHF, adversarial training, or robustness

✨ Nice to Have

• Experience in safety work for AI model deployment
• Strong engineering skills in deep learning

🎁 Benefits & Perks

• 💰 Competitive compensation including equity