In-depth technical expertise in AI security threats, vulnerabilities, and attack techniques.

Deep understanding of the OWASP Top 10 and the OWASP Top 10 for Large Language Model (LLM) Applications.

Proven experience in designing and securing agent-based AI architectures, including tool invocation, memory management, agent communication, and workflow orchestration.

Experience implementing AI security testing and assurance practices, including red teaming, threat modeling, threat hunting, and risk assessments.

Strong scripting and automation skills, with experience developing security tooling, scripts, and automated pipelines.

Solid understanding of cloud security principles and controls, particularly within Microsoft Azure and AI/ML environments.

Hands-on experience with AI platforms such as Azure AI Foundry, AWS Bedrock, Google Vertex AI, or similar managed LLM services is an advantage.

Agile, adaptable, and passionate about working in a fast-paced, collaborative, and dynamic environment.

Highly motivated and proactive, with a strong sense of ownership and a commitment to continuous learning and professional development.

Nice to have: experience securing Generative AI (GenAI) pipelines, including data ingestion, model training, evaluation, and deployment, against adversarial attacks, prompt injection, model manipulation, and data poisoning.