Engineering Manager, Inference Infrastructure

Highlights

• Own the control plane routing every Claude request across the inference fleet.
• Lead ML platform engineers improving throughput, latency, and reliability.
• Shape fleet strategy across clouds and heterogeneous hardware.

What they offer

• Optional equity donation matching
• Generous vacation and parental leave
• Flexible working hours

Ideal candidate

A systems-minded engineering leader who thrives owning critical production infrastructure and loves quantitative, measured impact. You coach strong engineers, create clarity across teams, and are curious how transformer inference shapes systems.

Requirements

• Engineering management experience leading critical-path production infrastructure at scale
• Deep systems background in load balancing, scheduling, orchestration, autoscaling or networking
• Experience shipping performance or efficiency improvements with measurable impact
• Experience running production infrastructure with on-call, incident response and deploy discipline
• Results-oriented approach balancing throughput, latency, cost, stability and velocity
• Ability to build strong relationships across team boundaries
• Curiosity about ML systems and how transformer inference works