Engineering Manager II, Agent Runtime

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.

About the role

The Agent Runtime team is a platform team at the heart of Box's AI-first strategy. You will own the runtime engine that enables every Box product team to deploy and operate AI agents at scale, supporting tenants like Box Notes, Canvas, Automate, and Workflows. This role leads a tight-knit team of six engineers (a hybrid of software engineers and ML engineers), works cross-functionally with product and engineering leaders across the company, and presents weekly progress directly to VP-level stakeholders.

Responsibilities

• Lead and grow a six-person hybrid team of software engineers and ML engineers building and operating Box's agent runtime platform.
• Own the onboarding of internal tenant teams onto the agent runtime, partnering closely with PMs and engineering managers across multiple product organizations to support their agent deployments.
• Drive the technical architecture of the agent runtime service, including the context retrieval layer, ensuring reliability, scalability, and quality.
• Champion an eval-driven development culture — define evaluation frameworks, run agent quality assessments, and use data to guide the team's technical direction.
• Manage and coordinate the team's on-call rotation to ensure timely and effective incident response, actively participate in escalated on-call incidents to provide leadership and support, and drive improvements by addressing recurring issues to minimize disruptions and deliver an enterprise-grade platform.
• Present weekly plans, progress, and demos to VP-level leadership, maintaining high visibility and accountability for the team's execution.
• Contribute directly to technical solutions — including code — when the team needs it, modeling the player-coach approach that defines this team's culture.

Requirements

• 7+ years of software or ML engineering experience with strong technical fundamentals in distributed systems and ML systems.
• 2+ years of engineering management experience leading hybrid teams of software engineers and ML engineers.
• Hands-on experience with AI agents or LLM-based systems, including agent architectures (ReAct, planner-based, or similar), evaluation methodologies (recall, precision, NDCG, LLM-as-judge), and deploying customer-facing agents in production at scale.
• Ability to thrive in ambiguous, fast-moving environments where priorities shift with the industry.
• Strong cross-functional collaboration skills, with experience working with multiple teams outside your own org.
• Familiarity with LangGraph or other agent harness frameworks (e.g., Dspy, AutoGen) is a plus.

Schedule

Boxers are expected to work from their assigned office a minimum of 3 days per week.

Pay

Redwood City Pay Range: $217,000 USD - $271,500 USD. This role is also eligible for equity and benefits.