Principal Engineer, AI/ML Security

About the job

Responsibilities

• Partner with Product Security and Engineering leadership to integrate AI security controls into customer-facing products.
• Collaborate with Security Data Science and Engineering to build, deploy, and monitor AI/ML models, guardrails, and automations.
• Lead adversarial testing and AI red teaming, including jailbreaking, prompt-injection, evasion, and poisoning.
• Conduct security reviews of major AI product initiatives from design to launch, providing architectural sign-off and escalation guidance.
• Perform threat modeling across the AI lifecycle, including data ingestion, training, evaluation, model serving, RAG, agent frameworks, and post-deployment monitoring.
• Define and drive the company's AI Security strategy and multi-year roadmap, prioritizing investments and risk management.
• Architect and lead the AI Risk & Governance framework, establishing policies and controls for AI/ML systems.
• Represent AI security at executive and board-level briefings, communicating risk posture and strategic decisions.
• Define the company's position on emerging AI security topics such as agentic AI and model supply chain risk.

Requirements

• 10+ years of experience in cybersecurity, with 4-5 years focused on AI/ML security, adversarial machine learning, or security data science in a production cloud or technology environment.
• Demonstrated track record of defining and driving AI or security programs at an organizational level.
• Deep, practitioner-level knowledge of adversarial ML attack and defense techniques.
• Ability to evaluate and synthesize academic AI security research into engineering guidance and policy.
• Experience engaging executive and senior leadership audiences on technical risk.
• Strong programming skills in Python and Go for building security tooling and automation.
• Proficiency in reviewing and critiquing AI/ML system architectures.
• Hands-on experience with AI red-team and defensive tooling, and model supply-chain frameworks.
• Bachelor's or Master's degree in Computer Science, Information Security, Mathematics, or equivalent practical experience.
• Fluency in OWASP LLM Top 10, MITRE ATLAS, NIST AI RMF, ISO/IEC 42001, and the EU AI Act.
• Prior experience in a cloud provider, security product company, or large-scale internet platform.
• Familiarity with LLM security in production, including RAG pipelines and agentic frameworks.

Benefits

• Annual bonus plan
• New hire equity grant
• Compensation Range: $230,400 - $288,000