Engineering Manager, Inference Infrastructure
Anthropic · San Francisco, CA | New York City, NY | Seattle, WA
About this role
**Engineering Manager, Inference Infrastructure** **About the Role** Lead a critical team building the control plane that coordinates Anthropic's inference fleet. You'll own decisions about request routing, capacity allocation, and system performance across all Claude deployments. This deeply technical role requires architectural expertise in distributed systems, load balancing, and fleet orchestration. **Key Responsibilities** • Own the technical roadmap for inference fleet coordination—traffic routing, capacity placement, caching, and control plane protocols • Partner with product, inference, performance, and capacity teams to identify and ship throughput, latency, and cost improvements • Build quantitative modeling practices—measure wins before and after shipping • Set technical strategy for heterogeneous hardware, multi-cloud deployments, and all serving surfaces • Run operational backbone: on-call, incident response, postmortems, deploy safety • Develop and retain strong teams; hire against a high technical bar • Coach engineers through shifting priorities and growing team structure **Minimum Qualifications** • Engineering management experience leading critical-path production infrastructure teams at scale • Deep systems background (load balancing, scheduling, cluster orchestration, autoscaling, distributed state, high-performance networking) • Shipped performance/efficiency improvements in large-scale systems with quantified impact • Production infrastructure operations experience: on-call, incident response, capacity planning • Results-oriented, impact-driven approach balancing throughput, latency, cost, and stability • Strong cross-team relationship building skills • Curiosity about ML systems and transformer inference **Preferred Qualifications** • 5+ years of engineering management experience • LLM inference serving experience (KV caching, continuous batching, request scheduling) • Cluster scheduler/autoscaler/load balancer/fleet control plane experience at scale • Multi-cloud or partner platform workload experience • Heterogeneous accelerator fleet background • Supercomputing or hyperscaler infrastructure leadership • Experience leading multiple teams through rapid growth **Compensation & Logistics** $405,000–$625,000 USD annually Bachelor's degree or equivalent required. Hybrid role (25%+ office time). Visa sponsorship available. San Francisco headquarters. *Anthropic encourages applications from all candidates, including those who don't meet every qualification.*
Listing freshness
CronJobs last confirmed this listing 19h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.