GenAI Security Researcher: Adversarial Defense

MACHINE LEARNING TECHNOLOGIES LLC; Charlotte (NC); On-site; USD 83,000 - 138,000; Full time

Job summary

MACHINE LEARNING TECHNOLOGIES LLC is seeking a Cyber Security Research Engineer to advance adversarial GenAI security research and bolster threat-driven risk management. You will collaborate with senior leadership and apply systems thinking, game theory, and intelligence analysis to strengthen AI defenses.

The role requires expertise in GenAI architectures, prompt engineering, and GenAI risk frameworks, with hands-on use of tools like Jira, ServiceNow, Confluence, and modern AI platforms.

Qualifications

• Advanced knowledge of Generative AI architectures and LLMs.
• Hands-on prompt engineering and adversarial assessment planning.
• Understanding of GenAI risks like data poisoning and prompt injection.
• Familiarity with OWASP Top 10 LLM 2025, MITRE ATLAS, and NIST AI RMF.
• Experience managing GenAI assessments and security testing.
• Awareness of regulations, ethics, and safety in GenAI.
• Experience with GenAI platforms and implementing security controls.

Responsibilities

• Strengthen AI red team initiatives and threat-driven risk management.
• Collaborate with senior leadership on security strategy and controls.
• Apply systems thinking and game theory to security challenges.
• Conduct scenario-based GenAI security testing and risk assessments.

Skills

GenAI architectures

Prompt engineering

GenAI risks

Robustness evaluation

GenAI assessments

Regulatory awareness

GenAI platforms

Tools

Jira

ServiceNow

IBM OpenPages

Confluence

ChatGPT

Gemini

Claude

Power BI

Microsoft Office

Job description

MACHINE LEARNING TECHNOLOGIES LLC is seeking a Cyber Security Research Engineer to advance adversarial GenAI security research and bolster threat-driven risk management. You will collaborate with senior leadership and apply systems thinking, game theory, and intelligence analysis to strengthen AI defenses.

The role requires expertise in GenAI architectures, prompt engineering, and GenAI risk frameworks, with hands-on use of tools like Jira, ServiceNow, Confluence, and modern AI platforms.