AI Cybersecurity Red Team Expert (Indian National)

AI Cybersecurity Red Team Expert

We are seeking a skilled AI Cybersecurity Red Team Expert to assess the security, robustness, reliability, and safety of AI systems. The role will focus on identifying vulnerabilities, simulating adversarial attacks, conducting AI security assessments, and evaluating AI models against potential misuse and emerging threats.

Key Responsibilities

• Conduct security assessments of AI/ML models, algorithms, and AI-powered systems to identify vulnerabilities, risks, and weaknesses.

• Design and execute adversarial attacks, adversarial examples, and malicious inputs to evaluate model robustness and resilience.

• Perform AI red teaming, prompt injection, jailbreak, and model safety testing, particularly for LLMs and Generative AI systems.

• Assess risks related to AI misuse, data privacy, model security, bias, fairness, and ethical AI.

• Identify potential attack vectors and evaluate AI systems against relevant security standards, regulations, and ethical guidelines.

• Collaborate with AI developers, data scientists, cybersecurity teams, and engineers to remediate identified vulnerabilities.

• Document testing methodologies, vulnerabilities, findings, risk levels, and recommended remediation actions.

• Research emerging AI security threats, attack techniques, and adversarial testing methodologies.

Qualifications & Skills

• Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Cybersecurity, or a related field.

• Proven experience in AI security, AI red teaming, adversarial testing, or ethical AI.

• Strong understanding of machine learning algorithms, neural networks, and AI/ML frameworks.

• Good knowledge of cybersecurity principles, penetration testing, and vulnerability assessment.

• Strong proficiency in Python; knowledge of R or Java is an advantage.

• Hands-on familiarity with tools/frameworks such as Foolbox, CleverHans, and Adversarial Robustness Toolbox (ART).

• Strong analytical, problem-solving, documentation, and communication skills.

Preferred Skills

• Hands-on experience with Large Language Models (LLMs), Generative AI, and AI agents.

• Practical experience in prompt injection, jailbreak testing, adversarial prompting, and model safety evaluations.

• Knowledge of AI security frameworks, data privacy regulations, and responsible/ethical AI practices.

• Experience assessing AI systems for model abuse, data leakage, prompt manipulation, and security vulnerabilities.

• Relevant certifications such as CEH, CISSP, or AI/ML security certifications are an advantage.