Staff+ Software Engineer, Inference Runtime

Anthropic•Seattle, WA

5h•$405,000 - $485,000•Hybrid

About The Position

Anthropic's Inference organization serves Claude to millions of users and enterprise customers with the speed, reliability, and efficiency that frontier AI demands. We build across GPUs, TPUs, and Trainium, and the complexity of our development environment grows with every platform we add. We're looking for a Staff Engineer to be a technical lead for Inference Runtime: the team that owns the shared, accelerator-agnostic core of our inference serving stack, whose performance, correctness, and abstractions every accelerator builds on. This is a senior IC role with broad technical ownership. You'll set technical direction for the runtime's architecture, its release and validation systems, and the workflows engineers use to develop on top of it. You will partner across Inferencing to make hard calls on boundaries, prioritization, and tradeoffs across heterogeneous accelerator platforms. You'll pair with the team's Engineering Manager, who owns hiring and people development, while you own the technical roadmap and drive the work, representing the team in cross-org efforts spanning serving, scaling, and accelerator teams. This role is for someone who has been the technical anchor of a platform with many internal consumers, who thinks in systems and feedback loops, and who gets real satisfaction from building abstractions that hold up as the system scales another order of magnitude.

Requirements

Deep background in systems engineering or ML infrastructure, with the ability to go hands-on with performance profiling, latency and throughput optimization, and systems debugging at scale
Real depth in at least one accelerator ecosystem (CUDA/GPU, TPU, or Trainium/AWS Neuron) and genuine appetite to keep the runtime agnostic across all of them
Have significant software engineering experience, with a strong background in high-performance, large-scale distributed systems serving millions of users
A track record of defining and using engineering metrics to drive improvement: you've set SLOs on platform surfaces, and driven escape rates, release times, latency, or throughput in a measurable direction
Experience driving technical alignment across organizational boundaries, advocating for your team's needs while contributing to shared infrastructure
Strong written and verbal communication, and the ability to influence technical direction without formal authority

Nice To Haves

8+ years of software engineering experience, with significant time as the technical lead or anchor on a platform, inference runtime, or ML infrastructure team
Experience with ML compiler toolchains (XLA, Triton, NeuronX) or accelerator driver/firmware management at scale
Background operating production as a validation surface at scale: shadow traffic, canary populations, automated baseline comparison, fast rollback
Experience with deterministic or simulation-based testing for hardware-dependent systems
Experience with CI/CD systems at scale, particularly for workloads involving accelerator hardware
Familiarity with Kubernetes-based development and job scheduling environments
Prior tech lead experience on a developer productivity or platform engineering team at a fast-growing AI/ML company

Responsibilities

Set technical direction for the team, owning the architecture and roadmap for the shared runtime of the inference serving stack
Own and evolve the accelerator-agnostic runtime itself – its interfaces, internal boundaries, and build structure – including hands-on work in a performance-sensitive Rust and Python codebase
Keep the platform's expansion cost low by ensuring new models and deployment targets pay only for their own specialization, and edge cases stitch back into the core easily
Drive efficient accelerator usage – utilization, scheduling, memory management – across GPU, TPU, and Trainium
Build the runtime's validation surface around partitioned builds, change-scoped testing, and canary/shadow/rollback as first-class mechanisms
Act as a technical counterpart to Anthropic's central Infrastructure org on the compilers, build systems, and toolchains the runtime depends on, contributing Inference's performance and correctness requirements, and making the call on build vs. adopt
Mentor engineers on the team through design review, code review, and direct collaboration, raising the technical bar without owning headcount