AI Security Engineer

Kinaxis is a global leader in modern supply chain orchestration, and they are seeking an AI Security Engineer to design, implement, and operate security controls for AI-enabled systems. The role involves serving as a subject matter expert in AI security and contributing to the maturation of AI security frameworks and operational practices.

Responsibilities:

• Design and implement end‑to‑end security guardrails across the AI lifecycle, including data ingestion, training, evaluation, deployment, and runtime monitoring
• Develop secure‑by‑default patterns for AI enabled applications
• Implement controls for agentic workflows, including tool permissioning, action constraints, auditability, and blast‑radius reduction
• Define and enforce secure configuration baselines for AI services such as cloud AI platforms, model gateways, vector databases, and model runtimes
• Lead AI security design reviews, conduct threat modeling, and risk assessments for AI-enabled systems
• Identify AI-specific risks and translate findings into prioritized mitigation plans, updated standards, and actionable engineering guidance
• Monitor emerging AI threats, vulnerabilities, and research, incorporating relevant insights into security practices, documentation, and team enablement
• Plan and execute targeted adversarial testing against AI enabled applications and workflows
• Develop repeatable test cases to evaluate resistance against misuse, data leakage, and unsafe output
• Partner with internal offensive security teams and external assessors to validate resilience before launch and during major changes
• Evaluate, deploy, and operate AI security controls
• Define logging and telemetry requirements for AI enabled systems
• Ensure AI security events are integrated into centralized monitoring and response workflows
• Serve as a subject‑matter expert for AI security, advising product and engineering teams on secure design choices and risk trade-offs
• Contribute to the evolution of AI security standards and governance practices
• Collaborate with engineering leaders to embed AI security requirements into CI/CD and MLOps pipelines, aligned with secure SDLC practices
• Serve as an escalation point for complex AI security investigations and abuse scenarios

Requirements:

• Bachelor's degree in Information Security, Computer Science, Engineering or equivalent practical experience
• 6 – 8 years of experience in security engineering, application security, cloud security, or security architecture, including hands‑on work securing production systems
• Strong understanding of secure software development practices and modern cloud platforms
• Demonstrated experience securing production AI-enabled systems
• Excellent written and verbal communication skills, with the ability to clearly articulate complex technical information
• Strong analytical, communication, and prioritization skills in fast‑moving environments
• Continuous learning
• Deep understanding of LLMs, agents, RAG pipelines, model serving, and MLOps
• Strong grasp of AI-specific threats (prompt injection, jailbreaks, model inversion, poisoning, data leakage)
• Experience deploying AI security defenses (LLM firewalls, policy engines, input/output validation, DLP, monitoring)
• Experience building secure-by-design patterns and defense-in-depth for AI systems
• Ability to define telemetry, logging, and detection strategies for AI systems
• Ability to design and implement security controls across AI tools, platforms, and delivery pipelines
• Hands-on experience performing AI/ML threat modeling
• Ability to translate AI risks into actionable controls and engineering requirements
• Experience testing AI systems against adversarial attacks and abuse scenarios
• CISSP
• CAISP
• CSSLP
• SABSA
• Cloud Provider Security Certifications
• NIST AI RMF Training or ISO/IEC 42001 Lead Implementer