Engineering Manager II, Agent Runtime

Box•Redwood City, CA

22d•Hybrid

About The Position

Box is building the infrastructure that powers AI agents across our entire product ecosystem — and we need a hands-on engineering leader to run it. 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 is not a team that ships features in isolation — it is the foundation that makes Box's agent-powered products possible. You will lead a tight-knit team of six engineers (a hybrid of software engineers and ML engineers), work cross-functionally with product and engineering leaders across the company, and present weekly progress directly to VP-level stakeholders. If you are energized by fast-moving, ambiguous environments where the work you do has immediate and visible impact on the business, this is the role for you.

Requirements

7+ years of software or ML engineering experience
Strong technical fundamentals — comfortable with distributed systems, 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
Ability to speak fluently about agent architectures (ReAct, planner-based, or similar), evaluation methodologies (recall, precision, NDCG, LLM-as-judge), and the real-world challenges of deploying customer-facing agents in production at scale
Thrive in ambiguous, fast-moving environments where priorities shift with the industry
Adapt quickly, keep the team focused, and deliver customer value even when the plan changes.
Natural cross-functional collaborator who has worked with multiple teams outside your own org — partnering with product managers and engineering leaders across different organizations is where you do some of your best work.

Nice To Haves

Familiarity with LangGraph or other agent harness frameworks (e.g., Dspy, AutoGen) is a plus, though equivalent experience with other agent architectures is equally valued.

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.