AI/ML Application Security Engineer

Primary Responsibilities:

• Lead the design and implementation of AI/ML security controls across model development, training, deployment, and production operations.
• Conduct threat modeling, adversarial testing, red teaming exercises, and AI attack simulations to identify and mitigate risks within LLMs, RAG architectures, agent-based systems, and AI-powered applications.
• Develop secure-by-design standards for AI platforms, including model registry policies, deployment guardrails, training data validation processes, and secure model evaluation frameworks.
• Assess and defend against emerging AI threats, including prompt injection, jailbreaking, model extraction, model evasion, data poisoning, agent hijacking, output manipulation, data leakage, and business logic abuse.
• Design and maintain AI security architecture, security specifications, security documentation, SOPs, data flow diagrams, and network topology documentation.
• Implement monitoring capabilities for AI environments, including security telemetry, usage logging, production monitoring, anomalous model behavior detection, and AI incident management processes.
• Partner with Security Operations teams to support threat detection, security investigations, incident response activities, forensic analysis, and AI-related threat intelligence initiatives.
• Evaluate and secure integrations involving APIs, vector databases, agent frameworks, external tools, and third-party AI services.
• Ensure alignment with industry frameworks and regulatory requirements including NIST AI RMF, NIST CSF, SOC 2 Type II, ISO 27001, and other applicable compliance standards.
• Provide technical leadership, mentoring, and security guidance across engineering and business stakeholders while communicating risks and recommendations to both technical and non-technical audiences.

Key Qualifications:

• 7+ years of experience in cybersecurity, security engineering, application security, product security, or a related discipline, including hands-on experience securing AI/ML technologies.
• Strong knowledge of Large Language Models (LLMs), artificial intelligence, machine learning concepts, AI/ML lifecycle security, and secure AI development practices.
• Experience performing threat modeling, adversarial machine learning assessments, offensive security testing, red teaming, and security risk assessments.
• Deep understanding of OWASP LLM Top 10, MITRE ATLAS, AI governance principles, and AI risk management methodologies.
• Experience securing AI applications that leverage Retrieval-Augmented Generation (RAG), multi-agent workflows, vector databases, and agent frameworks.
• Hands-on knowledge of web application security, API security, authentication, authorization, rate limiting, abuse prevention, and sensitive data protection controls.
• Proficiency with Python and familiarity with modern AI development ecosystems including LangChain, LlamaIndex, Hugging Face, and OpenAI APIs.
• Experience with SIEM, EDR, security monitoring platforms, SOC operations, incident response, and threat detection technologies.
• Background supporting regulated environments and compliance frameworks such as SOC 2 Type II, ISO 27001, and NIST-based programs.
• Strong communication, stakeholder management, technical writing, requirements gathering, and cross-functional collaboration skills.

This position is based onsite in Chautauqua County, New York, within the greater Buffalo metropolitan region, and offers the opportunity to help secure cutting-edge AI technologies 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 stakeholders supporting the development and delivery of innovative immunotherapy treatments to combat cancer and infectious diseases.