AI Product Security Engineer (Contract) - NA

Job Description At Synoptek, we think globally and act locally. As the world's first Managed Experience Provider (MxP™), Synoptek provides world-class strategic IT leadership and hyper-efficient IT operational support, enabling our global client base to grow and transform their businesses. We are excited to add experienced talent to our team. The AI Product Security Engineer is responsible for designing, implementing and validating security controls for Synoptek's AI-enabled products. This contract role combines product security architecture with software engineering to protect enterprise data, integrations and automated actions. The engineer anticipates emerging AI risks and translates security requirements into practical, tested product capabilities. The role works with product engineering, applied AI, infrastructure and security leadership to integrate safeguards throughout development and operations. Success is measured by implemented controls, repeatable security testing, documented risk decisions and achievement of agreed release criteria and engagement milestones. Mandatory Skills Product and application security, threat modelling, secure software development, security architecture, CI/CD security, LLM and agent security, multi-agent security, adversarial testing, identity and access management, least privilege, tool authorization, policy enforcement, RAG security, tenant isolation, Python, API development, Microsoft Azure, LangGraph, PowerShell, Windows execution environments, C#/.NET or TypeScript. Role Own AI product security architecture by defining security requirements, trust boundaries and control objectives for AI-enabled applications and integrations. Translate threat models into implementable designs, production code, tests and prioritized engineering work.Engineer identity, authorization and policy enforcement controls for access to data, services, tools and actions. Apply least privilege, appropriate approvals and independent enforcement throughout AI workflows.Secure automated and privileged execution by developing and validating safeguards for commands, scripts and automation runtimes, including authorization, input validation, runtime restrictions, credential scope and safe error handling.Protect endpoint integrations by engineering secure communication, deployment, update and recovery capabilities for software operating on endpoint devices. Validate compatibility with enterprise endpoint protection and operational requirements.Secure ingestion, indexing and retrieval by implementing permission-aware data access, sensitive-data protection and tenant isolation across enterprise search and retrieval-augmented generation (RAG) systems.Protect AI knowledge and memory by developing safeguards for source integrity, provenance and sensitive information. Test and mitigate risks associated with untrusted content, prompt injection and data poisoning.Build observability and containment capabilities by implementing security telemetry, monitoring and investigation mechanisms that protect sensitive information and support the detection, containment and recovery of unauthorized or unsafe behavior.Secure multi-agent workflows by designing and evaluating agent permissions, interactions, supervision and outcome verification against measurable security objectives and established security controls.Conduct adversarial testing and security acceptance by building repeatable tests for AI-specific attacks, authorization failures, data disclosure, tool misuse and unsafe interactions. Validate safeguards, permitted behavior and failure handling against realistic integrations and controlled test environments.Embed security into product delivery by contributing code and reviews, integrating security checks into CI/CD and maintaining regression coverage. Assess changes to components, integrations, dependencies and execution environments, and remediate findings before agreed release gates.Advance security through applied experimentation by anticipating emerging risks, evaluating new techniques and comparing effective safeguards against simpler alternatives using measurable protection, reliability, latency and cost.Deliver accountable security outcomes by establishing testable acceptance criteria and milestone evidence, documenting control limitations and recommending mitigations. Escalate residual-risk decisions to appropriate stakeholders. Secondary Responsibilities Maintain concise security design records, operational guidance and implementation documentation suitable for engineering handover.Share practical guidance with engineering teams through design reviews, technical discussions and knowledge transfer.Support security investigations and remediation planning relevant to the product and agreed engagement scope.Track relevant AI security developments and recommend improvements supported by testing and operational evidence. FLSA: Exempt EEO Statement: We are proud to be an Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, age, veteran status, sexual orientation, gender identity, marital status, pregnancy, genetic information, disability, or any other characteristic protected by law. Employment decisions are based on job-related factors. Location Boston, Massachusetts, United States (USA) Education Qualification Bachelor's degree in a relevant field and 6 years of experience in product security, application security or software engineering. Hands-on experience securing LLM-enabled or agentic products, multi-agent workflows, enterprise data access and privileged execution. Strong Python skills, with experience in APIs, cloud security, automated testing and CI/CD. Familiarity with Azure, PowerShell and C#/.NET or TypeScript. Desirable Skills Cloud-native security engineering, AI red teaming, security telemetry, incident investigation, endpoint security integration, automated security testing, applied AI security experimentation, security documentation and technical knowledge sharing. Experience 7 to 15 Years