Sr. Adversarial AI Security Engineer
Core
Design and deliver realistic adversarial cyberattacks, including AI-enabled and orchestrated attacks, to test the effectiveness of the security stack and the company's ability to detect and respond.
Role type
Senior IC adversarial AI security engineer
Builds
Adversarial simulation suites, proof-of-concepts (PoCs), and automated testing tools for LLM/RAG/agent systems
Domain
Financial services security, AI/ML adversarial defense
Deliverable
production ML models | product features | dashboards & analysis | research | client delivery | infrastructure
Required skills
offensive security/research, adversarial AI, Python, replay/fuzzing automation, MITRE ATLAST Framework, prompt injection testing, jailbreak testing, retrieval poisoning testing, model extraction testing, membership inference testing, agent tool-use abuse testing
Preferred skills
regulated environments experience, OSCP/GXPN certification, complex global environments experience
Technologies
LLM, RAG, agent systems, CI/CD pipelines
Responsibilities
Lead planning, design, and implementation of assessments focusing on AI/ML systems; Perform full scope adversarial simulation/red team assessments; Work with cyber defense teams to develop improved defense methods; Prepare reports containing attack paths, findings, and mitigation recommendations; Provide support during ongoing assessments by writing tools and setting up infrastructure; Research and evaluate emerging technologies and vendor solutions
Seniority
Senior, hands-on IC