Senior AI Security Engineer

Teleion Consulting is seeking a hands-on, client-facing Senior AI Security Engineer to help protect AI workloads and enterprise AI deployments. This contract role is based in Seattle, WA (onsite) and centers on securing large language models, agentic systems, AI gateway layers, and the governance and zero trust controls that support the full AI stack.

In this position, you will assess real production risks, implement centralized control for AI traffic, and strengthen how identity, tools, and data access are governed for AI agents and MCP (Model Context Protocol) tooling. The work also includes red teaming and shadow discovery to identify unsafe or unsanctioned AI usage across client environments.

Key Responsibilities

• Evaluate and mitigate AI and LLM attack surfaces in production, including prompt injection (direct and indirect), data leakage via model outputs, insecure tool use, jailbreaking, and model supply chain risk.
• Deploy, configure, and operate AI gateways and LLM proxy layers with centralized control, including model allowlists, per-team API keys, rate and budget limits, centralized audit logging, and inline guardrails for prompt injection, sensitive data egress, credential leakage, and unsafe output.
• Design and implement governance frameworks for agentic systems and MCP tooling, covering registries, approval workflows, runtime policy enforcement, and identity and authorization patterns for non-human identities.
• Implement OAuth-based access and token lifecycle management, along with scoped tool permissions for AI agents aligned to least-privilege principles.
• Extend zero trust controls to AI workloads across identity, device, network, application, and data pillars, with Azure preferred (Entra ID, Defender for Cloud, Key Vault, Purview, Conditional Access).
• Build monitoring and detection for AI systems, including prompt behavior analysis, tool invocation patterns, anomalous output detection, and data movement tracking.
• Run AI red team and adversarial testing to identify vulnerabilities using PyRIT, Garak, or equivalent tooling.
• Lead shadow AI discovery initiatives to identify unsanctioned AI applications and browser extensions across the enterprise.
• Perform third-party AI vendor security reviews and assess M365 Copilot security posture, including oversharing remediation and sensitivity label enforcement.
• Advise clients on AI governance frameworks, including OWASP Top 10 for LLM Applications, MITRE ATLAS, NIST AI RMF, and relevant compliance standards.
• Perform tasks as assigned.

Requirements

• 7+ years of security engineering experience, including at least 2 years directly securing AI, ML, or GenAI systems in production.
• Hands-on experience securing LLM and agent attack surfaces: prompt injection, jailbreaking, data extraction, capability chaining, and supply chain risk.
• Experience deploying or operating an AI gateway, LLM proxy, or centralized AI control plane with production-grade input/output guardrails and audit logging.
• Familiarity with agentic AI risk classes, such as excessive agency, capability chaining, tool and memory poisoning, and unsafe autonomous action.
• Experience implementing identity and authorization patterns for non-human identities in an AI or service-oriented context.
• Strong cloud security background with Azure preferred (Entra ID, Defender for Cloud, Key Vault, Purview, Conditional Access).
• AI red team experience using PyRIT, Garak, or equivalent tools.
• Python proficiency, including work with LLM APIs (OpenAI, Anthropic, Azure OpenAI) and security evaluation tooling.
• Knowledge of OWASP Top 10 for LLM Applications, MITRE ATLAS, and NIST AI RMF.
• Certifications preferred: CISSP, AZ-500, SC-100, or CCSP. Familiarity with ISO/IEC 42001 or EU AI Act is a plus.

Technologies

• Python
• OAuth
• PyRIT
• Garak
• MCP (Model Context Protocol)
• OpenAI
• Anthropic
• Azure OpenAI
• Azure
• Entra ID
• Defender for Cloud
• Key Vault
• Purview
• Conditional Access
• M365 Copilot
• OWASP Top 10 for LLM Applications
• MITRE ATLAS
• NIST AI RMF
• ISO/IEC 42001
• EU AI Act
• CISSP
• AZ-500
• SC-100
• CCSP

Compensation and Employment Details

• Location: Seattle, WA (onsite)
• Salary: USD 155,000 - 200,000 per year
• Job Type: contract

Benefits

• full benefits
• PTO
• holiday
• 401(k)