Senior Security Researcher (Red Team)

pindropsecurity; Stati Uniti; Ibrido; USD 180.000 - 230.000; Tempo pieno

Vantaggi offerti da questo lavoro

Remote-first environment

Unlimited paid time off

RSUs

Health, dental, and vision coverage

HSA employer contribution

Paid parental leave

Monthly phone and internet allowance

Learning and development stipend

Family-building benefits

Descrizione del lavoro

Pindrop Security is seeking a senior offensive security expert to probe AI-driven identity and trust systems. The role blends red team ops, GenAI attack simulation, and traditional cloud testing in a remote-first setup with regular on-site gatherings.

You will work closely with blue teams, product, and ML stakeholders to surface weaknesses, craft attack chains, and drive actionable remediation across GenAI pipelines and cloud environments.

Competenze

• 3+ years of hands-on penetration testing experience.
• Experience attacking AI systems, including GenAI and LLM-specific attack surfaces.
• Background in adversarial machine learning, LLM security, or voice/audio deepfake detection.
• Strong scripting skills with Python or comparable languages for offensive automation.
• Clear communication skills for translating technical findings into actionable guidance.

Mansioni

• Plan and execute red team operations against GenAI systems, LLM pipelines, RAG architectures, autonomous agents, APIs, SaaS products, and cloud environments.
• Conduct adversarial testing for prompt injection, indirect prompt attacks, jailbreaks, model extraction, training-data poisoning, data leakage, and inference abuse.
• Use deepfake generation and voice synthesis techniques to attempt defeating voice authentication and deepfake detection capabilities.
• Build novel attack chains combining GenAI vulnerabilities with infrastructure, application, identity, and API weaknesses.
• Run full-scope penetration tests, support bug bounty efforts, and perform architecture reviews, code reviews, and threat modeling.
• Build automation for offensive workflows, testing, compliance checks, alerting, and reporting using Python or similar scripting languages.

Conoscenze

Penetration testing

Python scripting

GenAI security

Adversarial ML

Cloud security

Strumenti

AWS

GCP

Descrizione del lavoro

Role overview

A senior offensive security role focused on attacking AI-driven identity and trust systems to surface weaknesses before adversaries do. The position blends red team operations, generative AI attack simulation, deepfake and voice-spoofing research, and traditional cloud and application penetration testing, partnering closely with blue-team, product, and ML stakeholders.

Responsibilities

• Plan and execute red team operations against GenAI systems, LLM pipelines, RAG architectures, autonomous agents, APIs, SaaS products, and AWS/GCP cloud environments.
• Conduct adversarial testing for prompt injection, indirect prompt attacks, jailbreaks, model extraction, training-data poisoning, data leakage, inference abuse, and unauthorized output manipulation.
• Use deepfake generation and voice synthesis techniques to attempt defeating voice authentication and deepfake detection capabilities.
• Build novel attack chains combining GenAI vulnerabilities with infrastructure, application, identity, and API weaknesses.
• Run full-scope penetration tests, support bug bounty efforts, and perform architecture reviews, code reviews, and threat modeling.
• Build automation for offensive workflows, testing, compliance checks, alerting, and reporting using Python or similar scripting languages.

Requirements

• 3+ years of hands-on penetration testing experience.
• Genuine practical experience attacking AI systems, including GenAI and LLM-specific attack surfaces.
• Background in adversarial machine learning, LLM security, or voice/audio deepfake detection.
• Strong scripting skills with Python or comparable languages for offensive automation.
• Clear communication skills for translating technical findings into actionable guidance for technical and executive audiences.

Nice to have

• Relevant certifications such as OSCP, GPEN, GWAPT, GXPN, CEH, or equivalent.
• Prior experience in voice biometrics, AI security, fraud prevention, or similarly high-risk product environments.

Benefits and work setup

• Remote-first environment with regular in-person team on-sites and company-wide events.
• Unlimited paid time off.
• Competitive compensation including RSUs.
• Health, dental, and vision coverage; HSA employer contribution; paid parental leave.
• Monthly phone and internet allowance, learning and development stipend, and family-building benefits including fertility and GLP-1 support.