Red Team - Security Researcher III
Core
Proactively compromise and evaluate the security posture of internet-facing traffic management, security platforms, and emerging AI/ML implementations via advanced adversary emulation.
Role type
Senior IC offensive security researcher (AI/LLM focus)
Builds
Custom exploits, C2 infrastructure, and offensive tooling leveraging AI to bypass modern security controls
Domain
Cybersecurity, AI/ML security, Cloud security
Deliverable
production ML models | product features | research | client delivery
Required skills
Offensive cybersecurity (Red Teaming, Advanced Penetration Testing), AI/ML security testing (prompt injection, model inversion, data poisoning, adversarial ML), Python/Go/C++/Rust programming, Advanced attacker tradecraft (persistence, evasion, memory injection, lateral movement), Cloud environments (AWS/Azure), AI frameworks (PyTorch, TensorFlow, Hugging Face)
Preferred skills
Published security research, CVEs, bug bounty successes, conference talks, Offensive security certifications (OSCP, OSEP, CRTO, CRTE, OSWE), Compromising major cloud environments, SaaS platforms, MLOps pipelines
Technologies
Python, Go, C++, Rust, AWS, Azure, PyTorch, TensorFlow, Hugging Face, MITRE ATLAS, OWASP Top 10 for LLMs
Responsibilities
Lead complex, objective-based Red Team operations targeting global infrastructure, products, and AI/ML deployments; Conduct specialized AI/LLM penetration testing; Research and develop custom exploits and offensive tooling; Perform deep-dive vulnerability research on enterprise environments and AI pipelines; Partner with Engineering and Blue Teams to translate findings into architectural improvements; Contribute to the security community through published research and conference presentations; Mentor internal teams on advanced threat actor mindsets
Seniority
Senior, hands-on IC