Senior Security Engineer, Agentic Red Team

Highlights

• Close the Agentic Launch Gap by catching novel AI risks before formal reviews.
• Execute multi-turn attacks on production AI models to expose reasoning flaws.
• Codify findings into automated guardrails for all Google agent developers.

What they offer

• 15% bonus target
• equity
• benefits

Ideal candidate

Offensive-minded engineer who thrives in high-velocity teams and partners closely with builders to turn complex AI risks into practical, lasting defenses.

Requirements

• Bachelor's degree in Computer Science, Information Security, or equivalent practical experience
• 5 years of experience in Red Teaming, Offensive Security, or Adversarial Machine Learning
• Experience with LLM architectures, agentic workflows and AI vulnerability classes
• Experience developing exploits for GenAI models such as prompt injection and training data extraction
• Experience working with product teams or in a startup-like environment
• Familiarity with AI safety benchmarks, evaluation frameworks and fuzzing techniques
• Ability to translate complex probabilistic risks into actionable engineering fixes
• Excellent coding skills in Python, Go, or C++ with experience building security tools