AI Research Scientist, AI Safety and Security

Highlights

• Advance frontier research on AI safety, security, and alignment.
• Design methods to detect and mitigate adversarial attacks and misuse.
• Work in a focused incubation team with broad scientist-engineer network.

What they offer

• bonus
• equity
• benefits

Ideal candidate

Research-driven problem solver passionate about safe, aligned AI who thrives in collaborative incubation teams and turning long-term safety goals into testable milestones.

Requirements

• Bachelor's degree in Computer Science, Computer Engineering, relevant technical field, or equivalent practical experience
• Currently has or is in process of obtaining a PhD in Artificial Intelligence, Machine Learning, Computer Security, related field, or equivalent practical experience
• Experience with AI safety, alignment, adversarial machine learning, robustness, security, red-teaming, interpretability, or trustworthy AI
• Experience in alignment techniques, reward modeling, RLHF, constitutional AI, jailbreak prevention, robustness, or attack detection
• Experience working with large language models and evaluating their safety properties
• 2+ years of industry experience in AI safety and security research
• Experience building systems based on machine learning and/or deep learning methods
• Track record via grants, fellowships, patents, or publications in ML, Security, or AI Safety venues