AI Pentester/Red Teamer

We are looking for a skilled AI Pentester to join our cybersecurity team and strengthen our offensive security and AI security testing capabilities.Job SummaryThe ideal candidate will combine strong penetration testing and red teaming expertise with hands-on experience using AI tools and Large Language Models (LLMs) to accelerate vulnerability discovery, exploit development, security automation, and security research. The role also involves evaluating AI-driven applications, validating findings, and delivering actionable security recommendations while maintaining strict ethical and data security standards.

Key Responsibilities

Conduct penetration testing, vulnerability assessments, red team exercises, and security research across applications, networks, infrastructure, and cloud environments.Leverage AI coding assistants and LLMs to enhance reconnaissance, source code analysis, vulnerability discovery, exploit development, and security testing automation.Develop and improve security tools, scripts, proof-of-concept exploits, fuzzing harnesses, and repeatable testing workflows.Perform AI/LLM security assessments, including prompt injection, jailbreaking, data leakage, model security, and adversarial testing.Evaluate the security of AI-integrated applications and assess risks associated with AI-generated code, outputs, and automated workflows.Assess detection and response capabilities by validating security controls, identifying potential detection gaps, and evaluating defensive technologies.Validate AI-generated findings, eliminate false positives, and verify vulnerabilities through controlled, authorized testing.Prepare comprehensive technical reports, executive summaries, risk assessments, and practical remediation recommendations.Collaborate with security, development, and infrastructure teams to improve security posture and integrate security testing into development lifecycles.Ensure all testing activities follow established authorization, ethical hacking, confidentiality, and data protection requirements.

Key Requirements

5+ years of experience in penetration testing, red teaming, or offensive security.6+ months of hands-on experience using AI tools in offensive security workflows.Strong knowledge of application, network, and infrastructure security, Web, & Mobile SecurityProficiency in Python, Bash, or similar scripting languages.Familiarity with LLM security, offensive security tools, and responsible AI practices.