Principal Engineer, AI/ML Security

Role overview Serve as the principal technical authority for AI/ML security on a large-scale cloud platform, reporting to the VP and Deputy CISO. This role blends hands-on adversarial testing, program leadership, and executive communication to set the multi-year strategy for securing AI systems and operationalizing ML-powered defenses.

Responsibilities - Define how AI security controls are integrated into customer-facing products, partnering with product security and engineering leadership. - Build, deploy, and serve in-house AI/ML models, guardrails, tooling, and automations, and monitor deployed models for drift and performance. - Lead adversarial testing and AI red-team exercises covering jailbreaking, prompt injection, evasion, and poisoning. - Conduct security reviews of major AI initiatives from design through launch, providing architectural sign-off and escalation guidance. - Threat model across the AI lifecycle including data ingestion, training and fine-tuning, evaluation, model serving, retrieval-augmented generation, agent frameworks, and post-deployment monitoring. - Own the multi-year AI security strategy and roadmap, and architect the AI Risk and Governance framework covering policies, standards, and controls. - Represent AI security at executive and board-level briefings and define organizational positions on emerging topics such as agentic AI, model supply chain risk, and synthetic data integrity.

Requirements - Ten or more years in cybersecurity, including at least four to five years focused on AI/ML security, adversarial machine learning, or security data science in a production cloud or technology environment. - Demonstrated success defining and driving an AI or security program at the organizational level rather than only executing within one. - Deep practitioner knowledge of adversarial ML attacks and defenses such as evasion, poisoning, model extraction, membership inference, and prompt injection. - Ability to read and synthesize academic AI security research and translate it into engineering guidance and policy. - Experience engaging executive audiences on technical risk and translating complex AI threat scenarios into business impact. - Strong programming skills in Python and Go with a track record of building security tooling and automation. - Proficiency reviewing AI/ML system architecture across data ingestion, feature engineering, training pipelines, model serving, and continuous monitoring. - Hands-on experience with AI red-team tooling, defensive tooling, and model supply-chain frameworks. - Bachelor's or Master's degree in Computer Science, Information Security, Mathematics, or a related field. - Practical experience securing production LLM systems, including RAG pipelines, agentic frameworks, and model APIs against prompt injection, jailbreaking, and data exfiltration.

Benefits and work setup - Remote role with a compensation range of $230,400 to $288,000, plus potential bonus and equity eligibility. - Conference, training, and education reimbursement, plus broad access to on-demand learning resources. - Comprehensive benefits package, an Employee Assistance Program, local meetups, and a flexible time-off policy.