Senior AI Security Engineer

Title: Senior AI Security Engineer

Location: Remote

Job Description

Key Responsibilities

•              Threat model AI/ML systems across the lifecycle (data ingestion, training, fine-tuning, deployment, inference).

•              Assess and mitigate AI-specific attack classes such as prompt injection, jailbreaks, data poisoning, adversarial examples, and insecure agent and tool-use patterns.

•              Secure the ML pipeline and supply chain, including model provenance and the evaluation of third-party and open-source models.

•              Advise on compliance alignment (e.g., NIST AI RMF, EU AI Act, OWASP).

•              Establish AI security policies, standards, and secure-development guidance for teams building with AI.

•              Partner with detection & response teams to extend monitoring and incident response to AI-related incidents.

•              Help govern sanctioned vs shadow AI use; review and harden 3rd-party AI vendors and integrations.

•              Create and monitor controls around AI prompts, data movement and AI guardrails across the AI stack for the organization.

•              Continuously monitor the AI threat landscape and translate research into actionable engineering mitigations.

•              Partner with IT and cross-functional teams outside of Information Security offering technical expertise around secure use and adoption of AI.

•              Enable customer-facing teams by developing AI security guidance and reference materials, supporting customer briefings and workshops, and serving as a technical subject-matter expert in customer engagements.

Required Qualifications

•              Bachelor’s degree in Computer Science, Software Engineering, Information Security, or a related field or equivalent hands-on experience.

•              Minimum 8 years of experience in security engineering, information security, or related technical disciplines, with a demonstrated focus on securing AI/ML systems.

•              Proven experience defining and executing enterprise security strategies.

•              Experience and deep technical knowledge of how AI/ML technologies work.

•              Deep familiarity with AI security frameworks (e.g., NIST AI RMF, MITRE ATLAS, OWASP).

•              Experience securing organizational tool stacks including cloud-based, hybrid or on-prem solutions.

•              Deep knowledge of AI related threats, risks and mitigation strategies.

•              Strong foundation in core security principles—threat modeling, secure design, and identity and access control—applied to AI/ML systems and the infrastructure that supports them.

•              Hands-on experience securing AI/ML systems, including practical AI red teaming against LLMs, agentic workflows, or RAG systems

•              Strong programming and scripting proficiency (e.g., Python) for building security tooling, automation, and test harnesses across the AI/ML lifecycle.

•              Hands-on experience securing cloud and containerized environments (AWS, Azure, and/or Google Cloud Platform; Kubernetes and containers), including the infrastructure on which AI/ML workloads are trained, deployed, and served.

•              Experience embedding security into MLOps and AI/ML development pipelines (and the CI/CD workflows that feed them), including model and dataset integrity checks, guardrail validation, and automated security testing.

•              Proven ability to communicate complex security risk clearly to both technical and non-technical audiences, including engineers, leadership, and customers.

•              Demonstrated experience mentoring engineers and serving as a senior technical authority and subject-matter expert.

•              Hands-on offensive security and AI red-teaming experience targeting AI systems—including prompt injection, jailbreaks, data poisoning, model extraction, and agent/tool-abuse techniques—along with familiarity testing the web, API, and infrastructure layers these systems depend on.

Preferred Qualifications

•              Hands-on experience with AI/ML security tooling and AI security posture management (AI-SPM) platforms (e.g., Wiz AI-SPM, Protect AI, HiddenLayer, Lakera, or comparable model-scanning and guardrail solutions), complemented by familiarity with broader cloud and enterprise security platforms.

•              Hands-on experience securing AI/LLM-enabled and agentic applications, including deep familiarity with OWASP Top 10 for LLM Applications, OWASP Top 10 for Agentic AI, MITRE ATLAS, NIST AI RMF, and Model Context Protocol (MCP) security implications.

•              Practical experience with agent frameworks and orchestration (e.g., LangChain/LangGraph, CrewAI, AutoGen, or custom agent architectures) and with LLM evaluation, observability, and red-teaming tooling for testing model and agent behavior.

•              Experience operating within governance, risk, and compliance frameworks, with exposure to enterprise AI adoption, third-party/vendor AI risk assessment, and AI policy or standards development.

•              Experience in client-facing, consulting, or pre-sales roles, translating AI security concepts for customer and executive audiences through briefings, workshops, or advisory engagements.

•              Industry certifications such as CISSP, OSCP, or AWS/Azure/Google Cloud Platform security certifications; emerging AI-security-specific credentials (e.g., AI red-teaming or AI/LLM security certifications) are especially valued.