What You Will Do
Lead AI Security Architecture: Drive the technical roadmap and high-level design to continuously prevent, detect, and autonomously contain threats across our systems and AI agents.
Hands-on Prototyping & POCs: Build proof-of-concepts for autonomous agent harnesses that automatically detect, analyze, and mitigate security vulnerabilities in real-time.
AI SDLC Optimization: Architect non-bypassable security guardrails across the SDLC for both developers and AI coding agents to ensure production systems are secured by default.
Red Teaming & Adversarial Validation: Proactively execute adversarial testing by simulating real attack scenarios across APIs, AI systems, and infrastructure to validate defense mechanisms.
Protect AI Systems: Design deep technical defenses to protect all AI agents and experimental features from prompt injection, system misuse, manipulation, and unauthorized actions.
Zero-Trust Governance: Architect a Zero Trust Identity Control Plane that eliminates implicit trust, ensuring access for both humans and autonomous agents is time-bound, least-privileged, and continuously verified.
Technical Leadership & Influence: Act as a security expert and IC leader. Mentor security engineers, provide architectural guidance across the organization, and partner closely with ML, DevOps, and Platform teams to evangelize secure coding practices without direct reporting lines. What You Will Need Experience: 10+ years of hands-on technical experience across different areas of security, including infrastructure security, product security, system design, and DevSecOps.
AI/ML Security Expertise: Proven track record of leveraging coding agents and LLMs for security workflows, Red Teaming GenAI models, and building defenses against jailbreaking, adversarial ML, and model hallucination risks.
DevSecOps & Cloud Mastery: Deep technical proficiency with cloud platforms like AWS or GCP, including their security tools, Docker, and containerization technologies.
Technical Proficiency: Proficiency in programming languages such as Java, Node.js, and Python, combined with hands-on experience securing production code, developing security tooling, and performing manual source code reviews.
Strategic Vision & Threat Modeling: Ability to architect secure-by-default platform capabilities so all services inherit baseline security automatically, paired with advanced threat modeling skills for AI-native and distributed architectures.
Bonus Points
Relevant certifications such as GIAC Web Application Penetration Tester (GWAPT) or OffSec’s Advanced Web Attacks and Exploitation (WEB-300).
Strong understanding of emerging AI security frameworks (e.g., MITRE ATLAS, NIST AI RMF).
Experience participating in bug bounty programs or speaking at meetups/conferences.
Developing Security products and frameworks.
