Agentic AI Developer - PAN INDIA GDS Location

Your Key Responsibilities

• Lead AI red teaming execution including prompt injection, jailbreak and data exfiltration scenarios
• Perform AI threat modelling across model, data, and application layers
• Design and implement LLM guardrails and RAG security controls
• Conduct ML pipeline and model lifecycle security reviews
• Secure APIs and AI inference endpoints in cloud environments
• Support incident response for AI-specific threats and exploitation attempts
• Integrate security controls into AI/ML pipelines and DevSecOps workflows
• Collaborate with SOC teams for AI workload detection and monitoring use cases

Skills and Attributes for Success

• Strong understanding of ML/GenAI concepts (LLMs, embeddings, pipelines)
• Hands-on experience in application security, API security and cloud security
• Knowledge of AI attack surfaces (prompt, model, data layers)
• Adversarial mindset with ability to simulate real-world attack scenarios
• Understanding of OWASP Top 10 and LLM vulnerabilities
• Working knowledge of MITRE ATT&CK framework

To Qualify for the Role

• 36 years of experience in cybersecurity, application security or cloud security
• Hands-on exposure to AI/GenAI security concepts or implementations
• Experience in vulnerability assessment, red teaming or threat modelling
• Working knowledge of cloud platforms (Azure/AWS)

Ideally, You’ll Also Have

• Hands-on experience with AI security tools such as Garak, PyRIT, LLM Guard
• Exposure to adversarial ML tools (ART, Foolbox)
• Experience integrating security into MLOps/DevSecOps pipelines
• Certifications in cloud or security domains (AZ-500, CEH, etc.)

What We Look For

• A self-driven cybersecurity professional with strong technical depth in AI security and the ability to independently drive security testing and implementation for enterprise AI workloads.

What We Offer

• Opportunity to work on advanced AI security engagements, exposure to global clients, and continuous learning in AI-led cyber defence and adversarial testing methodologies.