Engineering Manager, Agent

Descript Descript · AI Frontier · San Francisco, CA · Engineering

Engineering Manager for Descript's Agent team, focused on building the Agentic Video Editor, Underlord. The role involves managing a team of 5-6 software engineers, driving product experience for agentic video editing, leading experimentation, strengthening Evals, and partnering with AI Research on exploratory improvements. The team is scaling its agent infrastructure and product experience.

What you'd actually do

  1. Own execution: Manage team prioritizes, drive alignment across stakeholders, adapt plans to maximize outcomes, and hold a high bar for delivery through active planning, prioritization, and follow-through
  2. Define team direction: Connect customer needs, product vision, and technical realities in close collaboration with Product, Design, and AI Research by setting clear priorities and making tradeoffs to deliver results
  3. Develop your team: Recruit, mentor, and grow engineers, fostering a culture of continuous learning and high performance. Create stretch opportunities for ICs, deliver clear and direct feedback, and manage underperformance early
  4. Drive operational excellence: Ensure execution is predictable, reliable, and sustainable, implementing best practices in project management and engineering processes
  5. Maintain the technical bar: Guide architectural decisions, ensure sound design tradeoffs, address tech debt that slows execution, and drive delivery of high-quality, reliable systems

Skills

Required

  • 5+ years of software engineering experience
  • 2+ years of engineering management experience delivering complex, cross-functional product work with high velocity and quality
  • Excels at hiring, developing, and retaining strong engineering talent, and creating collaborative, empowering, and high-performing team environments
  • Strong technical background with the ability to guide architectural decisions, evaluate tradeoffs, and maintain engineering excellence without being hands-on day-to-day
  • Communicates clearly and effectively across technical and non-technical audiences, and thrives in collaborative environments working closely with Product, Design, and Research partners
  • Plans ahead on a 12+ month horizon, but prioritizes and re-prioritizes aggressively as new information emerges. Makes and communicates calculated bets.
  • Thrives in fast-paced, rapidly changing environments, with the ability to navigate ambiguity and drive results.
  • High ownership and a bias toward action is a must.

Nice to have

  • Experience building agents
  • developing evals
  • leading teams building LLM-powered products
  • Experience building creative tools in the past or you're a frequent user of creative media tools.

What the JD emphasized

  • AI moves very quickly and keeping pace with the market means you are already behind.

Other signals

  • Agentic Video Editor
  • multimodal nature of video
  • Agent Quality flywheel
  • novel context management strategies
  • RL/new model development
  • multimodel explorations