TECHNICAL LEAD - Penetration Testing

Penetration Tester – AI Security & Application SecurityRole Overview

We are seeking a skilled Penetration Tester with strong expertise in Application Security and emerging AI Security testing. The role involves conducting comprehensive security assessments across web, mobile, API, cloud, and AI-powered applications, identifying vulnerabilities, and providing actionable remediation guidance.

Key Responsibilities

• Perform penetration testing of web applications, mobile applications, APIs, thick-client applications, cloud-native environments, and network infrastructure using both manual and automated techniques.
• Conduct security assessments of AI/GenAI-powered solutions, including AI chatbots, AI agents, LLM-based applications, and Model Context Protocol (MCP) implementations.
• Execute AI security test cases covering prompt injection, jailbreak attacks, sensitive data exposure, harmful content generation, tool misuse, hallucinations, grounding failures, excessive agent privileges, and policy bypass scenarios.
• Design and execute adversarial testing techniques to evaluate the effectiveness of AI models, guardrails, and security controls.
• Identify, validate, and prioritize security vulnerabilities based on severity, exploitability, and business impact.
• Prepare detailed assessment reports including findings, risk ratings, supporting evidence, proof-of-concept demonstrations, and remediation recommendations.
• Collaborate with development, security, and project teams to validate vulnerabilities, communicate risks, and support remediation efforts.
• Stay updated on evolving cybersecurity threats, AI security risks, attack vectors, and penetration testing methodologies.
• Contribute to security testing standards, methodologies, templates, reporting frameworks, and process improvements.

Required Skills & Experience

• Bachelor's degree in Computer Science, Information Security, Cybersecurity, or a related field.
• 4+ years of hands-on experience in Vulnerability Assessment and Penetration Testing (VAPT).
• Strong expertise in OWASP Top 10 (Web, API, LLM Security), Agentic AI Security, MCP security, SANS Top 25, PTES, OSSTMM, and NIST frameworks.
• Minimum 2+ years of practical experience assessing GenAI and LLM security risks, including prompt injection, model manipulation, data leakage, insecure outputs, hallucinations, and model abuse scenarios.
• Experience developing and executing structured AI security testing methodologies and test cases.
• Hands-on experience with security assessment tools such as Burp Suite and HCL AppScan.
• Good understanding of SAST, DAST, and modern application security testing practices.
• Strong knowledge of application architecture, secure coding practices, SDLC, authentication mechanisms, cryptography, and security protocols.
• Relevant security certifications such as OSCP, OSWE, CEH, or equivalent are preferred.
• Excellent verbal and written communication skills in English.

Preferred Competencies

• Strong analytical and problem-solving skills.
• Ability to independently manage security assessments and meet project timelines.
• Experience working with cross-functional and globally distributed teams.
• Strong stakeholder management and presentation skills.
• Ability to clearly document testing scope, assumptions, limitations, evidence, and security recommendations.

Engagement Expectations

• Deliver high-quality security assessment outcomes within agreed timelines.
• Collaborate effectively with internal and external stakeholders throughout the engagement lifecycle.
• Support occasional coordination across global time zones when required.
• Maintain thorough documentation of testing activities, findings, and recommendations.
• Demonstrate a proactive, self-driven approach to delivering security testing engagements.