AI Quality & security engineer

Responsibilities Define quality engineering frameworks for AI agents, LLM systems, and autonomous workflows. Design validation strategies covering functionality, reasoning quality, grounding, safety, compliance, and robustness. Conduct adversarial testing, red-teaming, prompt injection testing, jailbreak testing, and model abuse simulations. Build AI evaluation harnesses and automated quality gates within AI-DLC pipelines. Define AI governance controls, risk management practices, and compliance mechanisms. Validate agent decisions, tool usage, workflow execution, and operational behavior. Partner with engineering teams to improve trust, safety, and resilience. Qualifications Bachelor's or Master's degree in Computer Science, AI, Cybersecurity, or related discipline. Experience in Quality Engineering, Security Engineering, or AI Validation. Knowledge of AI security, adversarial machine learning, prompt attacks, OWASP LLM Top 10, and Responsible AI. Experience with model evaluation platforms, red-team frameworks, and automated testing solutions. Understanding of Agentic AI control systems and human-in-the-loop governance models. Experience working in regulated environments.