Description

Design and implement automated security controls, threat modeling, and secure SDLC pipelines for agentic AI systems and LLM pipelines.

This role is on-site.

Responsibilities

• Design automated model access control, inference authorization, and policy-driven prompt validation for agentic systems.
• Implement continuous threat modeling for LLM pipelines, agent orchestration, and AI gateways.
• Build secure reference architectures enforcing AI guardrails via configuration as code, runtime policy engines, and automated testing.
• Create plugins, hooks, and skills using Claude Code or Microsoft AI Foundry to automate secure SDLC workflows.
• Operate automated SBOM and AI BOM pipelines, integrating vulnerability analysis into CI/CD and deployment gates.

Required Skills

• 5+ years of experience in DevSecOps, CI/CD, and secure software development lifecycles.
• Strong hands-on experience with SAST, DAST, SCA, secrets detection, container scanning, and IaC scanning.
• Deep knowledge of MLOps and AI/ML security, including prompt injection, model misuse, and data leakage prevention.
• Experience integrating security tooling via APIs and pipelines, not manual review.
• Proficiency in operating systems, cloud platforms, and hybrid environments.
• Ability to interpret and secure code in multiple languages with automation as the primary mitigation strategy.
• Understanding of cybersecurity, privacy, and AI governance requirements.

Preferred Skills

• Experience with Copilot Studio, Claude Code, or Microsoft AI Foundry.
• Ability to teach and develop agentic AI workflow automation.

Key Skills

Education

Bachelor's degree