Inference Engineering and Product Lead

Highlights

• Own direction of LLM inference platform serving frontier open-source models at scale.
• Lead serving stack, routing and agentic optimization for low-latency inference.
• Partner with category-defining customers like Cognition, DoorDash and Ramp.

What they offer

• Equity

Ideal candidate

A hands-on engineering leader who loves building high-performance infrastructure and coaching strong teams. You are customer-obsessed, thrive on hard distributed systems problems, and want to shape frontier AI inference.

Requirements

• 10+ years of industry experience, including 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 including Linux kernel, file systems, and containers