Remote-First Senior Red Team Researcher - GenAI Security

Pindrop; United States; Remote; USD 99,000 - 165,000; Full time

Benefits offered by this job

RSUs

Remote-first environment

In-person team events

Unlimited PTO

Health plan

HSA employer contribution

Vision & Dental plans

Parental Leave

Phone and internet allowance

Learning & Development stipend

Job summary

Pindrop is seeking a Senior Security Researcher (Red Team) to proactively identify and exploit weaknesses across product, cloud, and AI-powered systems, strengthening defenses before adversaries do. You will blend hands-on offensive security, GenAI attack simulation, security engineering, and collaboration with blue-team and product stakeholders.

Responsibilities include designing red team operations, testing prompt injection and model extraction, using deepfake techniques to assess voice

Qualifications

• 3+ years of hands-on pen testing and red team experience across SaaS, cloud, APIs, and web apps.
• Experience attacking GenAI/LLM-based systems; prompt injection, jailbreaking, model extraction.
• Hands-on with deepfake tools, voice synthesis, or audio/visual spoofing.
• Proficiency with offensive security tooling: Burp Suite, ZAP, Nmap, Metasploit, Cobalt Strike.
• CI/CD integration of SAST/DAST tools.
• Python or similar scripting for custom tooling.
• Familiarity with AI security tools like Garak, PyRIT, Claude Security.
• Understanding cloud security, container security, API security, and standards (ISO 27001, NIST, CIS, PCI DSS, SOC 2).

Responsibilities

• Design and lead red team ops against GenAI systems, LLM pipelines, and cloud environments.
• Test prompt injection, jailbreaking, model extraction, and data leakage scenarios.
• Use deepfake and voice synthesis to test authentication and detection capabilities.
• Create end-to-end threat scenarios by chaining GenAI and infrastructure weaknesses.
• Conduct full-scope penetrations and support bug bounty across web apps and AWS/GCP.
• Perform architecture reviews, threat modeling, and security code reviews for AI/ML components.
• Build automation for offensive workflows and detections using Python and tooling.
• Collaborate with SecOps to translate findings into remediation plans.
• Stay current on GenAI security research and regulatory developments.

Skills

Penetration testing

Red team

GenAI security

Cloud security

Python scripting

CI/CD security tests

Adversarial ML tooling

Threat modeling

Tools

Burp Suite

OWASP ZAP

Nmap

Metasploit

Cobalt Strike

Job description

Pindrop is seeking a Senior Security Researcher (Red Team) to proactively identify and exploit weaknesses across product, cloud, and AI-powered systems, strengthening defenses before adversaries do. You will blend hands-on offensive security, GenAI attack simulation, security engineering, and collaboration with blue-team and product stakeholders.

Responsibilities include designing red team operations, testing prompt injection and model extraction, using deepfake techniques to assess voice