TECHNICAL LEAD - Penetration Testing

Contract Scope Responsibilities Core Penetration Testing: Conduct detailed penetration testing of web applications, mobile applications, thick clients, cloud-native applications, APIs, and network environments using both automated tools and manual testing techniques. AI/LLM Security Testing: Assess AI chatbots, AI agents, and Model Context Protocol (MCP)-based applications, including risks introduced by AI systems and how those risks can be tested, governed, and reduced. Execute hands-on AI security test scenarios covering prompt injection, jailbreaks, harmful outputs, sensitive data leakage, tool misuse, hallucination, grounding failures, and policy bypass. Design and run adversarial prompts to test model and guardrail robustness. Reporting Remediation: Identify, classify, and prioritize vulnerabilities based on risk and business impact, and prepare clear reports with findings, evidence, and proof-of-concept details where applicable. Collaboration Delivery Support: Work with internal security, development, and project teams to understand application functionality, validate risks, communicate findings, and support remediation discussions within the agreed engagement scope. Stay current with emerging security threats, vulnerabilities, technologies, and testing methodologies. Contribute to agreed security testing templates, reporting formats, methodologies, and process documentation where required for the engagement.