Red Team Security Lead

Liberty Personnel Services, Inc.; Wayne (PA); On-site; USD 90,000 - 140,000; Full time

Job summary

Liberty Personnel Services, Inc. is seeking an AI Red Team Specialist to challenge security in AI-driven and traditional environments.

Wayne, PA based, you will simulate adversarial attacks on chatbots and ML models, and design red team campaigns across AI and standard infra. Collaborate with data science, fraud and engineering teams to translate findings into actionable improvements and risk insights for leadership.

Qualifications

• Offensive security experience with scripting (Python/Bash).
• Hands-on with security testing tools (Metasploit, Burp Suite).
• Familiarity with AI/ML security and cloud workloads.

Responsibilities

• Simulate adversarial attacks on chatbots, ML models and recommender systems.
• Design and execute red team campaigns for AI and traditional infra.
• Collaborate with data science, fraud and engineering teams to drive remediation.
• Translate technical risks into clear business insights for leadership.
• Evaluate vulnerabilities and prioritize remediation efforts.
• Balance AI-specific testing with standard red team methodologies.

Skills

Python scripting

Bash scripting

AI/ML security

Tools

Metasploit

Burp Suite

TensorFlow

PyTorch

Scikit-learn

Job description

• Phone Number: Enter a valid 10-digit phone number.
• * Resume:
• Resume:

  Drag your file(s) to start uploading

  OR Browse files Resume is required.

Are you a Red Team Security professional who loves to push systems to their limits - especially those powered by Artificial Intelligence? We're seeking a skilled AI Red Team Specialist to help us identify and exploit vulnerabilities in both AI-driven and traditional environments.

Key Responsibilities

• Simulate adversarial attacks on chatbots, ML models, and recommendation systems to expose weaknesses.
• Design and execute red team campaigns targeting both AI systems and standard infrastructure.
• Collaborate with data science, fraud, and engineering teams to turn findings into actionable improvements.
• Translate complex technical risks into clear business insights for leadership.
• Evaluate vulnerabilities and help prioritize remediation efforts.
• Balance AI-specific adversarial testing with traditional red team methodologies.

Required Skills

• Strong offensive security experience, including scripting (Python, Bash) and tools such as Metasploit and Burp Suite.
• Understanding of how AI/ML models are developed, deployed, and secured; familiarity with TensorFlow, PyTorch, or Scikit-learn is a plus.
• Experience securing AI workloads in cloud environments such as AWS SageMaker and Azure ML.

#libertyjobs #it #security #redteam #ai #cybersecurity #midsenior