Free cookie consent management tool by TermsFeed AVP - AI Security | Antal Tech Jobs
Back to Jobs
10 Hours ago

AVP - AI Security

decor
Mumbai
6 - 10 Yrs
Information Technology
On-site
Full-Time
Antal International

Overview

Role Overview

We are seeking a proactive and technically strong VP, Cybersecurity to lead security assurance for our AI Security products. This individual will ensure that our AI Security offerings — designed to protect customer AI systems — are thoroughly tested, validated, and resilient against real-world threats.

The VP, Cybersecurity will lead red teaming, penetration testing, and adversarial attacks simulation projects to ensure our products defend effectively against attacks on AI/ML systems. The ideal candidate brings hands-on expertise in both classic infrastructure/mobile security and modern AI threat models, with the ability to translate security insights into product and engineering improvements.

Key Responsibilities

Lead rigorous pre- and post-deployment testing of Company's AI Security products to ensure they effectively prevent, detect and respond to AI-specific attacks (e.g., adversarial inputs, model extraction, prompt injection)
Design and execute evaluations of our AI protection tools, simulating real-world threat scenarios targeting LLMs, ML pipelines, and AI agentic systems
Collaborate with product and engineering to continuously improve defenses based on security test results, threat modeling, and vulnerability discovery
Oversee security validation pipelines across all product lines, with a special focus on security assurance for AI-focused solutions
Build and scale a security assurance function that includes penetration testing, red teaming, and continuous vulnerability scanning across mobile, cloud, and AI assets
Ensure the integration of SSDLC practices, including threat modeling and static/dynamic analysis, into the engineering workflow
Present the security findings to executive leadership, clients, and auditors, with clear risk analysis and actionable recommendations
Guide a growing team of security analysts and researchers focused on protecting both internal infrastructure and client-facing security capabilities
Align testing frameworks and documentation with industry standards (e.g., NIST AI RMF, ISO/IEC 42001, OWASP LLM Top 10)
Continuously monitor emerging trends in cybersecurity, AI/ML threats, adversarial techniques, and defense frameworks, proactively incorporating mitigations into product design ensuring Company’s products stay ahead of evolving attack vectors

Required Qualifications, Experience & Skills

Bachelor’s or Master’s degree in Computer Science, Cybersecurity, Information Security, or a related field; certifications such as CISSP, OSCP, or GIAC are a strong plus
8+ years of experience in cybersecurity, including 3+ years in leadership roles involving product or platform security
Proven expertise in vulnerability assessment, penetration testing, and security assurance across cloud-native and mobile platforms
Experience conducting or overseeing adversarial evaluations of AI/ML systems, including model-level attacks, prompt injection, and data poisoning
Familiarity with modern AI architectures (e.g., LLMs, agentic AI frameworks) and their unique security challenges
Practical knowledge of security testing tools such as Burp Suite, Nessus, Metasploit, OWASP ZAP, and optionally AI-focused tools like IBM ART, CleverHans, or PrivacyRaven
Deep understanding of SSDLC, secure architecture, and post-deployment hardening practices
Track record of successfully working with engineering, product, and compliance teams to integrate security into the software lifecycle
Strong leadership, communication, and stakeholder management skills; experience representing cybersecurity in front of customers, regulators, or exec teams.

Preferred Skills (Nice to have)

Familiarity with AI-specific security frameworks like NIST AI RMF, ISO/IEC 42001, and OWASP Top 10 for LLMs
Exposure to security testing of agent-based AI systems and tool-use frameworks (e.g., LangChain, AutoGen, ReAct)
Understanding of threat intelligence, anomaly detection, and red teaming techniques in AI contexts
Share job

Talk to us

Feel free to call, email, or hit us up on our social media accounts.
Social media