Research Scientist, AI Secure Code

Highlights

• Advance CodeMender research to detect and fix vulnerabilities at scale.
• Build evaluation pipelines and leaderboards for security agents.
• Deploy agentic vulnerability solutions into Google developer workflows.

What they offer

• 15% bonus target
• equity
• benefits

Ideal candidate

PhD researcher passionate about AI safety and security who loves building scalable tools and self-initiating ambitious vulnerability research that moves from prototype to real-world impact.

Requirements

• PhD in Computer Science, Computer Engineering or similar technical field or equivalent practical experience
• Experience with vulnerability research (e.g., auditing, reverse engineering, exploitation)
• Experience building infrastructure, developer tools, or ML-based applications
• Publication record in AI conferences (e.g., NeurIPS, CVPR, ICCV, ICLR)
• Experience building AI tools/agents for coding
• Strong proficiency in Python, C++, or Go
• Familiarity with machine learning frameworks and techniques (fine-tuning, reinforcement learning)
• Ability to self-initiate and a passion for AI safety and security