Engineering Manager, Scalable Inference Platform

Anthropic Limited; San Francisco (CA); Hybrid; USD 405,000 - 625,000; Full time

Benefits offered by this job

Competitive compensation

Benefits

Equity donation matching

Generous vacation

Parental leave

Flexible hours

Office space

Job summary

Anthropic Limited is seeking a senior leader to own the technical roadmap for the inference fleet, coordinating traffic, capacity, and caches across multiple clouds and surfaces. You will lead ML platform, infrastructure, and distributed-systems engineers, shaping architecture and scaling with the fleet.

You will drive performance improvements, establish robust on-call practices, and mentor engineers, ensuring reliability and efficiency as models and hardware evolve.

Qualifications

• Engineering management experience leading teams on critical-path production infrastructure at scale.
• Deep systems background with load balancing, scheduling, autoscaling, or similar.
• Ability to quantify impact with numbers including cost and latency improvements.

Responsibilities

• Own the technical roadmap for how the inference fleet is coordinated and how traffic and capacity are managed.
• Collaborate with product, inference engine, performance, and capacity teams to identify throughput and latency wins and implement measurable improvements.
• Develop quantitative modeling practices; require measurement before shipping and predict the impact.

Skills

Engineering management

Systems depth

Load balancing

Production infrastructure

Performance improvements

On-call experience

Cross-team collaboration

ML systems curiosity

Education

Bachelor's degree

Tools

Kubernetes

Borg-style systems

Job description

Anthropic Limited is seeking a senior leader to own the technical roadmap for the inference fleet, coordinating traffic, capacity, and caches across multiple clouds and surfaces. You will lead ML platform, infrastructure, and distributed-systems engineers, shaping architecture and scaling with the fleet.

You will drive performance improvements, establish robust on-call practices, and mentor engineers, ensuring reliability and efficiency as models and hardware evolve.