Tech Stack

Description

You will lead a team building the cluster-level routing and coordination layer for Anthropic's inference fleet, making real-time decisions on request routing, cache placement, and cross-replica coordination to maximize throughput and efficiency. You'll drive system-level performance improvements, manage operational excellence, and grow a team of deep distributed-systems engineers.

Requirements

• Systems depth for architectural calls and evaluating technical candidates
• Experience with distributed systems and production reliability
• Ability to analyze performance at kernel, network, and framework levels
• Experience building and managing a team of engineers
• Strong communication and cross-team collaboration skills

Responsibilities

• Drive system-level performance for cluster-level inference efficiency
• Own technical roadmap for routing, cache placement, and cross-replica coordination
• Set technical strategy for routing across heterogeneous hardware and serving surfaces
• Run team's operational backbone: on-call, incident response, postmortems, deploy safety
• Develop and retain engineering team, hire for OS and framework depth