Staff Product Manager, AI Security

Box; Redwood City (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Box is seeking a Staff Product Manager for AI Security to define and execute the product vision for secure agentic AI across Box’s Intelligent Content Management platform. You will collaborate with AI/ML engineers, security architects, and product teams to translate cutting-edge threat intel into scalable platform controls.

You will lead the design and delivery of guardrail systems, secure agent connectivity, and defense-in-depth strategies against prompt injection and other AI threats, while

Qualifications

• 8+ years of product management in enterprise B2B SaaS security or AI/ML infrastructure.
• Deep domain expertise in AI/ML security and prompt-injection defense.
• Experience with agentic architectures, multi-agent coordination, and model integration protocols.

Responsibilities

• Define product strategy, vision, and roadmap for AI Security and Guardrails across Box AI, Box Shield, and Box platform.
• Build guardrail frameworks and policy engines for autonomous agents and external model integrations.
• Secure MCP-based connectivity and APIs with strict authentication and boundary isolation.

Skills

AI Security

Agentic Guardrails

Model Context Protocol

LLM security

Threat modeling

Education

Bachelor's or Master's in CS/Cybersecurity/AI/Engineering

Tools

Model Context Protocol (MCP)

NeMo Guardrails

Llama Guard

Job description

Box (NYSE:BOX) is the leader in Intelligent Content Management. Our platform enables organizations to fuel collaboration, manage the entire content lifecycle, secure critical content, and transform business workflows with enterprise AI. We help companies thrive in the new AI-first era of business. Founded in 2005, Box simplifies work for leading global organizations, including JLL, Morgan Stanley, and Nationwide. Box is headquartered in Redwood City, CA, with offices across the United States, Europe, and Asia.

By joining Box, you will have the unique opportunity to continue driving our platform forward. Content powers how we work. It’s the billions of files and information flowing across teams, departments, and key business processes every single day: contracts, invoices, employee records, financials, product specs, marketing assets, and more. Our mission is to bring intelligence to the world of content management and empower our customers to completely transform workflows across their organizations. With the combination of AI and enterprise content, the opportunity has never been greater to transform how the world works together and at Box you will be on the front lines of this massive shift.

WHY BOX NEEDS YOU

As a Staff Product Manager for AI Security, you will be the strategic product leader responsible for defining and executing the product vision and roadmap to secure agentic AI capabilities, autonomous workflows, and generative AI integrations across the Box Intelligent Content Management platform. As enterprise AI evolves from single-prompt interactions to multi-agent architectures and autonomous agentic workflows, securing enterprise content against novel AI threats is a top priority for CISOs and security leaders worldwide — and existential to Box's mission.

In this high-impact individual contributor role, you will build and scale defense mechanisms for both Box's native agentic capabilities — including Box Agent — and external integrations connecting third-party agents and foundation models via Model Context Protocol (MCP) and enterprise APIs. You will partner closely with world-class AI/ML engineers, security architects, red-team researchers, and corporate security teams to translate the bleeding edge of AI threat intelligence into robust, scalable platform guardrails and enterprise security controls.

WHAT YOU'LL DO

• You will define and execute the product strategy, technical vision, and roadmap for AI Security and Agentic Guardrails across Box AI, Box Shield, and the broader Box platform ecosystem.
• You will build agent guardrail frameworks and policy engines to monitor, evaluate, and constrain autonomous agent behaviors across Box Agent, custom workflow agents, and external model integrations.
• You will secure agentic connectivity powered by Model Context Protocol (MCP) and third-party AI APIs, establishing strict authentication, context boundary isolation, dynamic permissioning, and secure tool execution.
• You will architect multi-layered defenses against advanced AI threats, including direct and indirect prompt injection, jailbreaking, training data extraction, system prompt leakage, and coordinated agentic attack swarms.
• You will partner with Engineering, Applied AI/ML Research, Security Architecture, and UX Design to deliver low-latency, enterprise-grade AI security controls that preserve developer velocity and user experience.
• You will drive key business and security efficacy metrics, including guardrail evaluation accuracy, prompt injection prevention rates, MCP integration adoption, and Shield / Enterprise Plus security revenue growth.
• You will collaborate with Product Marketing, Sales, Customer Success, and Compliance to lead GTM strategy and position Box as the gold standard in safe, trusted Enterprise Agentic AI.
• You will engage directly with enterprise customers, AI security working groups, and industry analysts to anticipate evolving AI attack vectors, validate product requirements, and guide industry best practices.

WHO YOU ARE

• You have 8+ years of product management experience building and scaling enterprise B2B SaaS security products, cybersecurity platforms, cloud security solutions, or AI/ML infrastructure platforms.
• You bring deep domain expertise in AI/ML security, LLM application security (e.g., OWASP Top 10 for LLM Applications), prompt injection defense, agentic guardrail frameworks, or model alignment and safety systems.
• You have a proven track record developing product strategies around agentic architectures, multi-agent coordination, tool-use and function-calling security, or model integration protocols such as Model Context Protocol (MCP).
• You have a strong understanding of emerging threat vectors targeting autonomous AI systems, including multi-turn adversarial attacks, indirect injection via ingested content, and coordinated agentic attack swarms.
• You have the technical acumen to partner with AI/ML research and engineering leaders on vector embeddings, semantic evaluation models, LLM latency trade-offs, API gateway security, and zero-trust data access control.
• You have exceptional analytical capability to define guardrail telemetry, track threat mitigation efficacy, and balance strict safety barriers with responsive AI interactions, along with proven executive presence to influence C-level security leaders and align cross-functional stakeholders.

Preferred Skills

• Experience working with frontier AI/LLM models, prompt evaluation frameworks, red‑teaming AI systems, or developing real-time guardrail runtime libraries (e.g., NeMo Guardrails, Llama Guard, or proprietary guardrail pipelines).
• Hands‑on familiarity with MCP (Model Context Protocol), agent orchestration frameworks, or semantic router architectures.
• Familiarity with enterprise compliance standards, zero‑trust architectures, data loss prevention (DLP), or AI governance frameworks (e.g., NIST AI RMF, ISO 42001).
• Technical background with a Bachelor's or Master's degree in Computer Science, Cybersecurity, Artificial Intelligence, Engineering, or equivalent practical experience.

Box lives its values, with community and in-person collaboration being a core part of our culture. Boxers are expected to work from their assigned office a minimum of 3 days per week.

At Box, we believe unique and diverse experiences benefit our culture, our products, our customers, our company, and our world. We aim to recruit a passionate, high-performing workforce that reflects the world we live in.

EQUAL OPPORTUNITY

We are an equal opportunity employer and value diversity at our company. We do not discriminate on the basis of race, religion, color, national origin, gender, sexual orientation, age, marital status, veteran status, disability, and any other protected ground of discrimination under applicable human rights legislation. Box strives to respect the dignity and independence of people with disabilities and is committed to giving them the same opportunity to succeed as all other employees. Inclusiveness is core to our culture at Box, and we strive to ensure you get the most from your interview experience.

Box is committed to fair and equitable compensation practices. Actual base salary (or OTE if commissionable role) is dependent upon factors such as: knowledge, skill level, experience, and work location. This role is also eligible for equity and benefits. For more information, check out our benefits and perks.