AI Red Team Engineer — Adversarial ML Security (Remote)

DeWinter Group; Campbell (CA); Remote; USD 68,880 - 241,080; Full time

Job summary

A leading technology recruitment firm is seeking an experienced AI Red Teaming Engineer for a 12-month remote contract. The candidate will perform adversarial attacks on AI models, develop automated security scripts, and collaborate with security teams to strengthen AI defenses. Ideal candidates should have over 4 years of experience in Cybersecurity and expertise in LLM security risks. Strong communication and Python scripting skills are required. This role offers competitive pay rates between $50/hr and $175/hr.

Qualifications

• 4+ years of experience in Cybersecurity or Penetration Testing.
• Deep expertise in LLM security risks and prompt engineering.
• Demonstrated ability to work autonomously.
• Experience with Python scripting, Linux, and cloud security protocols.
• Strong communication skills for status updates.

Responsibilities

• Perform adversarial attacks to identify security vulnerabilities.
• Develop automated probing scripts for model safety testing.
• Map potential 'logic holes' in AI agents.
• Collaborate with security teams on hardening strategies.
• Create reports prioritizing risks for engineering teams.

Skills

Cybersecurity

Penetration Testing

LLM security

Prompt engineering

Python scripting

Linux

Cloud security protocols

Communication skills

Job description

A leading technology recruitment firm is seeking an experienced AI Red Teaming Engineer for a 12-month remote contract. The candidate will perform adversarial attacks on AI models, develop automated security scripts, and collaborate with security teams to strengthen AI defenses. Ideal candidates should have over 4 years of experience in Cybersecurity and expertise in LLM security risks. Strong communication and Python scripting skills are required. This role offers competitive pay rates between $50/hr and $175/hr.