Senior Offensive Security Manager

Postman•San Francisco, CA

3h•Onsite

About The Position

Postman is seeking a Senior Manager, Offensive Security to lead the strategic direction of its offensive security program. This role involves building a new Offensive AI Security capability and partnering with CISO leadership on threat-informed defense. The successful candidate will shape the future of offensive security at Postman, aiming to make the company an industry leader in adversarial testing of AI systems, agentic workflows, and LLM integrations. The role requires demonstrating vulnerabilities through live exploits to foster a strong security culture within the engineering organization.

Requirements

Minimum of 8 years in offensive security (penetration testing, red teaming, vulnerability research, or exploit development).
At least 4 years in a people management or leadership capacity, including experience managing managers or tech leads.
Demonstrated experience attacking AI/ML systems (adversarial ML research, LLM red teaming, agentic system exploitation, or building offensive tooling for AI targets).
Understanding of AI attack vectors such as prompt injection, indirect prompt injection, tool-use confusion attacks, and RAG poisoning.
Demonstrated ability to build and scale an offensive security program from the ground up or significantly mature an existing one.
Experience setting OKRs, managing budgets, and presenting to executive leadership.
Deep understanding of the modern threat landscape and its application to cloud-native, API-first, and AI-native architectures.
Hands-on experience with AI-augmented pentesting tools (e.g., PentestGPT, Horizon3, custom LLM-based fuzzing) and AI red team frameworks (e.g., Microsoft PyRIT, Garak, custom harnesses).
Ability to manage non-deterministic AI outputs in offensive tooling and target systems.
Ability to present complex exploit chains, including AI-specific attack paths, to developers in an inspiring manner.
Preference for building automated 'exploit-as-code' validators over manual testing.
Ability to architect evaluation harnesses and adversarial test suites for ML models.

Nice To Haves

Track record of contributions to the offensive security or AI security community (conference talks, tool releases, published research, CVEs, or active participation in OWASP, MITRE, or similar working groups).
Relevant certifications such as OSCP, OSCE, OSEP, GXPN, GPEN, CRTP, or equivalent.
AI/ML-specific credentials (e.g., GIAC GMAI) are a differentiator.
Deep familiarity with AWS security primitives, cloud-native attack paths, and container/Kubernetes exploitation.
Experience with API-specific attack methodologies (BOLA, BFLA, mass assignment, GraphQL abuse, gRPC exploitation).
Familiarity with how offensive security outputs map to SOC 2 Type II, ISO 27001, ISO 42001, FedRAMP, or CMMC control evidence.

Responsibilities

Define and execute the multi-year offensive security roadmap, aligning Red Team, Purple Team, and continuous validation capabilities with Postman's threat landscape and business priorities.
Establish and scale a dedicated offensive capability for AI/ML systems, including adversarial testing of LLM integrations, agentic workflows, RAG pipelines, and model-serving infrastructure.
Develop AI threat intelligence by tracking the evolving AI threat landscape and translating research into red team playbooks and detection hypotheses.
Lead structured adversarial campaigns against Postman's LLM deployments and AI agents, targeting various vulnerabilities like prompt injection and data exfiltration.
Design and deploy AI-based penetration testing platforms and autonomous agents for continuous security validation.
Integrate automated breach and attack simulation (BAS) into CI/CD pipelines, including AI model deployment pipelines.
Build, manage, and scale a high-performing team of offensive security engineers, including specialized AI red team operators.
Identify and hire talent at the intersection of offensive security and AI/ML, and develop internal training paths for cross-skilling.
Lead live 'Exploitable Demonstrations' to educate engineering teams on vulnerabilities and AI-specific attack vectors.
Translate offensive findings into business-level risk narratives for executive leadership and stakeholders.
Partner with GRC on audit evidence and compliance posture derived from offensive operations.
Collaborate with Product Security, Security Operations, and Engineering to ensure offensive findings drive measurable improvements.