AI Cyber Security Engineer

• Architect and execute holistic protection strategies across all machine learning ecosystems, safeguarding training pipelines, inference nodes, feature repositories, and data flows.
• Analyze architectural vulnerabilities and run threat assessments targeting risks like model inversion, prompt manipulation, data corruption, and unauthorized exploitation.
• Engineer custom automated monitoring mechanisms and security tooling capable of identifying and neutralizing artificial intelligence threats, adversarial manipulations, and abnormal usage sequences.
• Partner directly with data science professionals to embed security protocols throughout the development lifecycle, conducting red team exercises and enforcing secure code standards.
• Harden external integrations, large language model interfaces, vector repositories, and agentic workflows through rigorous identity management, access controls, and logging protocols.
• Coordinate with infrastructure teams to lock down containerized clusters, hardware acceleration resources, registry tools, and continuous delivery systems against compliance standards.
• Establish advanced telemetry and monitoring systems to track suspicious platform usage, detect operational drift, and capture threat metrics.
• Lead digital investigations alongside incident management teams to analyze logs, platform activity, and potential model compromise during security events.
• Champion technical guidance and cross-functional mentorship regarding secure systemic design, threat landscapes, and defensive architectures.
• Formulate governance frameworks, corporate standards, and operational boundaries for ethical technology usage, covering prompt handling and dataset classification.

• Eight or more years driving hands-on security architectures across application, cloud, or infrastructure domains within live production environments.
• Hands-on familiarity with Artificial Intelligence Systems, Machine Learning Pipelines, Large Language Model Applications, Vector Search, and Machine Learning Operations Platforms.
• Demonstrated history establishing Authentication, Authorization, Secrets Management, Network Segmentation, and secure Continuous Integration and Continuous Delivery frameworks.
• Deep knowledge of Amazon Web Services, Microsoft Azure, Google Cloud Platform, Docker, and Kubernetes.
• Technical mastery of risks like Data Poisoning, Model Theft, Adversarial Attacks, Model Inversion, Prompt Injection, and Jailbreaking.
• High proficiency using Python, Go, or Java.
• Solid expertise in Secure Software Development, Code Review, and Security Design Review.
• Outstanding communication skills to articulate risks and technical trade-offs to non-technical business partners and engineering peers alike.

Annual base salary spans $135,000 to $150,000, with eligibility for a discretionary bonus and equity, alongside a comprehensive benefits package.

StaffRight Associates has been retained by a premier industry innovator to spearhead the search for an exceptional technical leader to spearhead the protection of advanced intelligent systems. Operating in a hybrid capacity near Dunkirk, NY (three days on-site weekly), this pivotal direct-hire role offers the opportunity to architect robust protection frameworks, secure modern machine learning infrastructure, and shape the organizational strategy surrounding emerging technologies., When you partner with StaffRight Associates in your search for your next role, you’re doing more than pursuing a job, you’re aligning yourself with a team of experts committed to placing top-tier talent in truly impactful positions. We take pride in fostering professional growth and connecting forward-thinking individuals with organizations that value innovation and excellence. We look forward to showcasing your expertise in a way that resonates with our clients and opens the door to meaningful opportunities.