Sr. AI Cyber Security Engineer - Dunkirk / Buffalo NY

About the role

The Senior AI Cybersecurity Engineer is responsible for securing AI/ML systems end-to-end: from data pipelines and model training to deployment, monitoring, and abuse prevention. This role combines deep security engineering expertise with practical experience building or protecting machine learning and generative AI workloads.

Responsibilities

• Design and implement security controls for AI/ML platforms, including model training environments, inference services, data pipelines, and feature stores.
• Conduct threat modeling for AI systems, including model theft, data poisoning, prompt injection, model inversion, and abuse/misuse scenarios.
• Build and maintain security tooling and automation to detect and prevent AI specific attacks (e.g., adversarial inputs, prompt injection chains, anomalous usage patterns).
• Collaborate with data scientists and ML engineers to integrate security into the AI development lifecycle (secure coding, model validation, testing and red teaming for AI behaviors).
• Evaluate and harden integrations with third party AI providers (LLM APIs, vector databases, orchestration frameworks, agents), including authentication, authorization, data handling, and logging.
• Collaborate with cloud/platform teams to ensure AI infrastructure (Kubernetes, GPU clusters, model registries, CI/CD) follows security best practices and compliance requirements.
• Define and implement monitoring for AI systems, including abuse detection, drift and anomaly alerts, model access patterns, and security relevant telemetry.
• Partner with incident response teams on investigations involving AI systems, including analyzing logs, traffic, model behavior, and potential data/model compromise.
• Contribute to policies, standards, and guardrails for responsible and secure use of AI internally (e.g., data classification rules for training inputs and prompts, allowed use cases, evaluation requirements).
• Provide technical guidance and mentorship to other engineers on AI security concepts, threats, and secure design patterns.
• Create, edit and adhere to Standard Operating Procedures (SOPs), process improvements, and standardization of templates.

Requirements

Practical experience with AI/ML systems (e.g., working with ML pipelines, LLM applications, vector search, or MLOps platforms), whether as a security engineer or as an engineer collaborating closely with ML teams is required.

• Experience implementing authentication/authorization, secrets management, network segmentation, and secure CI/CD for services and APIs.
• Experience securing LLM and generative AI applications (e.g., RAG architectures, AI agents, chatbots, code assistants) is preferred.
• Experience with security logging/observability stacks (SIEM, data lakes, security analytics) and building detections for AI-related threats is preferred.
• Relevant certifications e.g., cloud security, offensive security, or AI-focused credentials is preferred.

Skills

• Strong understanding of modern cloud platforms (AWS, Azure, or GCP) and container/orchestration technologies (Docker, Kubernetes) as they apply to AI workloads.
• Solid knowledge of common AI/ML threat scenarios: data poisoning, model theft/exfiltration, adversarial examples, model inversion, prompt injection, jailbreaks, and abuse/misuse of generative models.
• Proficiency in at least one major programming language used in security and ML ecosystems (Python preferred; Go, Java, or similar also valuable).
• Strong background in secure software development practices, code review, and security design reviews.
• Ability to communicate complex technical risk and tradeoffs clearly to both technical and non-technical stakeholders.
• Hands-on work with ML stacks such as PyTorch, TensorFlow, scikit-learn, or ML platforms like SageMaker, Vertex AI, Azure ML, or on-prem equivalents.
• Familiarity with AI security and safety frameworks or guidance (e.g., NIST AI RMF, ISO/IEC AI standards, major cloud provider AI security patterns).
• Background in red teaming or offensive security focused on applications, APIs, or AI systems.

Qualifications

• Bachelor’s Degree with 8+ years of relevant experience is required; OR
• High school Diploma or equivalent with at least 12 + years of relevant experience is required.
• 5+ years of hands-on security engineering experience (application, product, cloud, or infrastructure), including designing and implementing security controls in production environments is required.

Benefits

No specific benefits listed in the provided job posting.

Pay

The annual base pay range for this position is $135,000 (entry-level qualifications) to $150,000 (highly experienced) annually.

Schedule

Regular work schedule is Monday – Friday, within standard business hours. Flexibility is available with manager approval.

Physical Environment

This is an on-site role based at ImmunityBio's state-of-the-art Dunkirk, New York campus, where collaboration and innovation drive everything we do.

ImmunityBio's Commitment to Diversity and Equal Opportunity

We are committed to providing you with the tools and resources you need to optimize your Health and Wellness. At ImmunityBio, we are an equal opportunity employer dedicated to diversity in the workplace. Our policy is to provide equal employment opportunities to all qualified persons without regard to race, gender, color, disability, national origin, age, religion, union affiliation, sexual orientation, veteran status, citizenship, gender identity and/or expression, or other status protected by law.