Inference Engineering and Product Lead

About Us:AI needs a new infrastructure layer. We're building it at Modal.

Every era of computing brought new workloads that previous infrastructure couldn't support: mainframes, databases, and the cloud. Each time, the company that rebuilt the layer underneath defined the decade. AI is no different, except it touches everything instead of one slice, and the window to build the layer underneath it is open right now.

Our customers include category-defining companies like Ramp, Cognition, DoorDash, and Suno. They rely on Modal for instant GPU access, sub-second container starts, and native storage, so it's simple to serve low-latency inference, fine-tune models, and access production-ready sandboxes at scale.

We've passed $1B in annualized run rate, up 15x from a year ago. In October 2026 we raised a $750M Series D led by Accel at a $15.75B valuation.

Our team includes creators of popular open-source projects (e.g.,Seaborn,Luigi), academic researchers, international olympiad medalists, and experienced engineering and product leaders with decades of experience.

The Role:

Modal's LLM inference platform delivers frontier performance for open-source models with best-in-class elasticity and developer experience, made in part possible by our custom runtime with GPU memory snapshots and multi-cloud substrate.

We're looking for a leader to own the direction and execution of this platform to continue to establish us as the clear market leader, working closely with customers like Cognition, Doordash, Ramp, and many more. You'll be leading a group of highly talented engineers working on our market-leading LLM inference offering, spanning the serving stack, routing infrastructure, internal agentic optimization platform, and the user-facing product surface area.

This is a hands-on leadership role — expect to split your time between technical contribution, product shaping and people management depending on what the team needs. You'll set direction, remove blockers, and build a strong engineering culture as your team tackles hard problems in distributed computing, frontier inference serving, and performance optimization.

What You'll Work On:

Team

• Recruit, hire, and grow a high-performing team of engineers; run regular 1:1s focused on coaching, feedback, and career growth

• Set clear performance expectations, hold a high bar, and build an environment where engineers do their best work

• Foster a culture of ownership, accountability, customer obsession, and continuous improvement

Technical and Product Direction

• Drive technical and product decisions through design reviews, code reviews, and architectural discussions

• Lead our efforts working with customers with novel or frontier workloads so they can be successful running on Modal

• Translate learnings from frontier customers into a roadmap for our internal optimization platform and user-facing product, so that gains from optimization and research efforts are accessible to all of our users

• Establish standards for reliability and product excellence; ensure the team owns projects end-to-end, from spec through production

Cross-Functional Leadership

• Partner with business operations and compute strategy on continuing to develop our strategy for compute purchases across a variety of accelerators

• Collaborate with GTM on product launches, positioning, and improving win rates for inference opportunities

• Help guide the roadmap for teams building the infrastructure platform underlying inference, as well as adjacent product teams

You May Be a Fit If:

• You have 10+ years of industry experience, including 3+ years in a leadership role

• You have a track record of building high-performance systems at scale

• You have a strong background in cloud infrastructure

• You have deep knowledge of low-level OS foundations (Linux kernel, file systems, containers, etc.)

Nice-to-Have:

• Experience working with LLM inference in production

• Familiarity with underlying concepts like engines, kernels, routing, KV cache management, and speculative decoding