Senior AI/LLM Penetration Tester
Core
Conducting cutting-edge security assessments of large language models, AI agents, and AI-powered applications to identify vulnerabilities and stay ahead of emerging AI threats.
Role type
Senior AI/LLM Security Consultant (Offensive Security)
Builds
Security assessments and red team exercises for production or pre-production AI systems
Domain
Cybersecurity / Artificial Intelligence / Large Language Models
Deliverable
client delivery
Required skills
Offensive security (penetration testing, red teaming), Prompt injection testing, Jailbreak techniques, Indirect prompt injection, Data leakage detection, Insecure tool/function calling analysis, Agentic AI abuse testing, Model misuse detection, Manual application security testing, Web application security (OWASP Top 10), API and cloud infrastructure security, Source code review, Dynamic testing, Python/JavaScript/Go/Java scripting, LLM orchestration frameworks, Adversarial machine learning concepts, Cloud-native AI platforms (Azure OpenAI, Amazon Bedrock, Google Vertex AI)
Preferred skills
AI red teaming against production systems, Research into emerging AI attack techniques, Building/securing AI agents, AI SDLC and governance frameworks
Technologies
Sliver, AImap, AWS, Azure, GCP, Azure OpenAI, Amazon Bedrock, Google Vertex AI
Responsibilities
Perform manual application security testing beyond automated scanning, Review AI application architectures and identify security weaknesses, Conduct source code review and dynamic testing, Present findings to technical and executive audiences, Mentor teammates and contribute to internal research and tooling development
Seniority
Senior, hands-on IC with mentorship responsibilities