Senior AI/LLM Penetration Tester

Bishop Fox
Remote

About The Position

Bishop Fox is seeking a Senior AI/LLM Security Consultant to join their team. This role focuses on helping clients stay ahead of emerging AI threats by conducting cutting-edge security assessments of large language models, AI agents, and AI-powered applications. Bishop Fox is a leader in offensive security, known for its proprietary Cosmos AI engine and its contributions to the open-source community. The company partners with many of the world's largest brands and has been recognized as a market leader in attack surface management.

Requirements

  • 5+ years of offensive security experience performing penetration tests, red team engagements, or application security assessments
  • Experience assessing AI/LLM-powered applications for vulnerabilities such as: Prompt injection, Jailbreak techniques, Indirect prompt injection, Data leakage and sensitive information disclosure, Insecure tool/function calling, Agentic AI abuse, Model misuse and unsafe output generation
  • Understanding of modern AI architectures
  • Experience performing manual application security testing beyond automated scanning
  • Strong understanding of web application security fundamentals, including the OWASP Top 10 Web, Agentic, and LLM Applications.
  • Experience reviewing AI application architectures and identifying security weaknesses across APIs, cloud infrastructure, and application logic
  • Experience performing source code review and dynamic testing
  • Familiarity with cloud platforms (AWS, Azure, or GCP) and securing AI workloads
  • Scripting or programming experience in Python, JavaScript Go, Java, or similar languages
  • Familiarity with LLM application and agent-orchestration frameworks, inference provider APIs, external capability integration for models, and open source tooling across commercial and self-hosted ecosystems.
  • Knowledge of authentication, authorization, networking, APIs, and secure software development practices
  • Excellent written and verbal communication skills, including presenting findings to technical and executive audiences
  • Ability to mentor teammates and contribute to internal research, tooling, and methodology development
  • Applicants must be authorized to work in the United States of America for the duration of employment without sponsorship.

Nice To Haves

  • OSCP, OSEP, GWAPT, GPEN, GXPN, or other relevant certifications
  • Bachelor's degree in Computer Science, Cybersecurity, or a related technical field
  • Experience conducting AI red team exercises against production or pre-production AI systems
  • Research into emerging AI attack techniques or contributions to the offensive security community
  • Experience building or securing AI agents and autonomous workflows
  • Knowledge of adversarial machine learning concepts and model security
  • Experience with cloud-native AI platforms such as Azure OpenAI, Amazon Bedrock, or Google Vertex AI
  • Familiarity with AI software development lifecycle (AI SDLC) and AI governance frameworks

Responsibilities

  • Conducting cutting-edge security assessments of large language models, AI agents, and AI-powered applications.
  • Performing penetration tests, red team engagements, or application security assessments.
  • Assessing AI/LLM-powered applications for vulnerabilities such as prompt injection, jailbreak techniques, indirect prompt injection, data leakage and sensitive information disclosure, insecure tool/function calling, agentic AI abuse, and model misuse and unsafe output generation.
  • Performing manual application security testing beyond automated scanning.
  • Reviewing AI application architectures and identifying security weaknesses across APIs, cloud infrastructure, and application logic.
  • Performing source code review and dynamic testing.
  • Mentoring teammates and contributing to internal research, tooling, and methodology development.

Benefits

  • Comprehensive benefits program tailored to meet your needs at an affordable price.
  • Employees are empowered to do their best work while advancing the security community through world-class research and consulting.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service