Senior AI Security Engineer

Primary Responsibilities

• Design, implement, and maintain security controls across the AI/ML lifecycle, including data pipelines, model training environments, model registries, inference services, and production deployments.
• Lead AI threat modeling initiatives and conduct security assessments of Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) applications, AI agents, vector databases, and other AI-driven technologies.
• Develop secure AI architectures and security design patterns to mitigate risks such as prompt injection, data poisoning, model theft, model inversion, model exfiltration, jailbreak attacks, adversarial machine learning attacks, and generative model abuse.
• Establish and maintain AI governance controls, AI guardrails, training data governance standards, prompt governance requirements, and responsible AI practices.
• Conduct AI security testing, AI system red teaming, application security reviews, API security assessments, and validation exercises to identify vulnerabilities and abuse scenarios.
• Partner with data science, machine learning engineering, infrastructure, and software development teams to integrate secure development practices throughout AI/ML pipelines and MLOps workflows.
• Build and enhance AI security monitoring capabilities, including anomaly detection, drift detection, observability, security telemetry, logging, and AI attack detection.
• Support incident response, threat detection engineering, security investigations, forensic analysis, and security operations activities involving AI systems and production environments.
• Secure cloud and on-premises AI infrastructure, including Kubernetes environments, GPU clusters, containerized workloads, CI/CD pipelines, APIs, authentication, authorization, secrets management, and network segmentation.
• Develop security standards, policies, SOPs, templates, and technical guidance while providing mentorship and leadership across cross-functional teams.

Key Qualifications

• Bachelor's degree in Computer Science, Cybersecurity, Information Technology, Engineering, or a related discipline, plus 8+ years of relevant experience in cybersecurity, security engineering, application security, product security, infrastructure security, or a related field. Candidates without a bachelor's degree may qualify with 12+ years of directly relevant professional experience.
• Hands-on experience securing AI/ML systems, machine learning platforms, generative AI applications, and enterprise AI environments.
• Strong understanding of AI/ML pipelines, model training, model validation, model deployment, secure model operations, and AI platform security.
• Experience designing and implementing secure AI architectures for LLM applications, RAG solutions, AI agents, and other modern AI workloads.
• Deep knowledge of AI-specific attacks and threats, including prompt injection, data poisoning, model theft, model inversion, model exfiltration, adversarial machine learning, jailbreak attacks, and AI misuse scenarios.
• Experience with cloud platforms including AWS, Microsoft Azure, and Google Cloud Platform (GCP), as well as Kubernetes, Docker, container orchestration, and cloud security best practices.
• Strong background in security monitoring, SIEM technologies, threat detection engineering, incident response, and security operations within production environments.
• Familiarity with modern machine learning technologies such as PyTorch, TensorFlow, Scikit-learn, SageMaker, Vertex AI, Azure ML, and on-premises ML platforms.
• Programming experience in Python and familiarity with secure software development, code reviews, and security design reviews.
• Knowledge of AI governance and compliance frameworks, including NIST AI RMF, ISO/IEC AI standards, AI security standards, AI safety frameworks, and evolving regulatory requirements.
• Excellent communication skills with the ability to perform technical risk assessments, communicate complex security concepts, and partner effectively with technical and business stakeholders.
• Relevant security, cloud security, offensive security, or AI-focused certifications are highly desirable.

This position is based onsite in Chautauqua County, New York, within the greater Buffalo metropolitan area, and offers the opportunity to help build and secure cutting-edge AI capabilities within a rapidly growing biotechnology organization. Located at the company's newly launched production facility on the scenic shores of Lake Erie, this role provides direct collaboration with research, manufacturing, engineering, and business leaders supporting the development and delivery of life-changing immunotherapy treatments. This is a hybrid position requiring regular in-person collaboration at the facility, typically 3 days per week..