Application Penetration Testing

Application Security enhances the ability of the development organization to consistently deliver highly functional applications that are secure and resilient against attack. We develop policies, processes, controls and tools to proactively embed security into developed applications.

seeking a Cyber Security Research Engineer to perform application security assessments on generative AI systems.

• Perform application penetration tests on LLMs and ML systems
• Evaluate open source and third-party solutions for red teaming gen AI systems
• Simulate adversarial scenarios: prompt leakage, indirect prompt attacks, model evasion, and inference abuse
• Meet with stakeholders to collect information and determine scope of testing
• Install, configure, use and maintain scanning and testing tools
• Perform manual testing to supplement results of automated scanning and testing tools
• Document identified security vulnerabilities and related matters in a clear, concise and timely manner

• Demonstrated detailed oriented self-starter and the ability to work independently with limited supervision and limited direction, and in collaborative team environments
• The ability to provide support after normal business hours as needed
• A strong ability to multi-task and manage varying priorities and projects
• Demonstrated excellent written and oral communication skills

• 4–8+ years in offensive security or penetration testing, with recent hands-on testing of AI/LLM systems
• 3–5 years of python development including python based API skills
• Demonstrated AI Engineering knowledge
• Experience with guardrails and bypass techniques
• Knowledge of LLMs, ML, RAG, embedding, vector DB concepts, Agentic AI concepts, ETL