Head of Inference Platform & Product

Modal; San Francisco, Northern (CA, KY); Hybrid; USD 250,000 - 360,000; Full time

Job summary

Modal seeks a hands‑on leader to own the direction and execution of its LLM inference platform, guiding a team of engineers across the serving stack, routing infrastructure, optimization tools, and user‑facing surface area.

You will balance technical contribution with product shaping and people management, setting standards for reliability and excellence while partnering with customers and cross‑functional teams to push frontier workloads to production at scale.

Qualifications

• 10+ years of industry experience including at least 3+ years in a leadership role.
• Track record building high‑performance systems at scale.
• Strong background in cloud infrastructure.
• Deep knowledge of low‑level OS foundations (Linux kernel, file systems, containers).
• Nice to have: experience with LLM inference in production and related concepts.

Responsibilities

• Lead a team of engineers focused on the LLM inference platform and related surface areas.
• Shape technical and product direction through reviews and architecture discussions.
• Collaborate with customers and cross‑functional teams to drive adoption and success.
• Establish reliability and ownership for end‑to‑end projects from design to production.

Skills

Leadership

Distributed systems

Cloud infrastructure

Linux/OS foundations

LLM inference experience

Job description

Modal seeks a hands‑on leader to own the direction and execution of its LLM inference platform, guiding a team of engineers across the serving stack, routing infrastructure, optimization tools, and user‑facing surface area.

You will balance technical contribution with product shaping and people management, setting standards for reliability and excellence while partnering with customers and cross‑functional teams to push frontier workloads to production at scale.