AI Security @Offensive Research Lead

About the job

Job Title: Senior Technical Lead — AI Security & Offensive Research

Location: Hyderabad / Bangalore / Chennai (Hybrid)

Employment Type: Full-time

Notice Period: Only Immediate Joiners

Experience: 8+ years in offensive security (with 2–3 years focused on AI/ML)

Role Summary

We are looking for a hands-on Senior Technical Lead to break, test, and secure our enterprise AI and machine learning systems. You will lead AI red teaming, build security guardrails, and act as our technical authority on AI vulnerability research.

Key Responsibilities

AI Penetration Testing: Test LLM and ML applications against attacks like prompt injection, jailbreaks, and data poisoning.

Red Teaming: Run adversary campaigns targeting MLOps pipelines and cloud infrastructure using frameworks like MITRE ATLAS.

Threat Modeling: Lead security and privacy design reviews across the whole AI lifecycle using STRIDE.

Vulnerability Research: Find and responsibly disclose new vulnerabilities (CVEs) in AI frameworks.

Requirements

Vulnerability Research: Must have one or more assigned CVEs or public security research disclosures (Hard Requirement).

AI Security: Proven experience in AI red teaming and penetration testing.

Coding & Tools: Strong Python skills for automation and custom tooling.

Cloud: Solid hands-on security depth in AWS, Azure, or GCP.

Shoot CV sunitha@perfectjobaccord.com  .