Adversarial AI Research Engineer

Job Summary

Adversarial AI Research Engineer is a full-time remote position focused on leading adversarial testing of AI systems, developing security frameworks, and collaborating with cross-functional teams to enhance AI security.

Key Responsibilities

• Lead adversarial testing of AI by designing and executing red team assessments to identify vulnerabilities
• Innovate AI attack techniques by integrating academic research with offensive security methods
• Build and scale security tooling to enhance automation in security testing across teams

Required Qualifications

• 6+ years of experience in offensive security, including red teaming and penetration testing
• 1+ years of hands-on experience testing AI/ML system security with knowledge of LLM vulnerabilities
• High proficiency in Python for tool development and assessment automation
• Experience leading complex technical projects and mentoring security teams