Anthropic· Software Engineering - Infrastructure· San Francisco, CA | Seattle, WA
Staff + Sr. Software Engineer, Cloud Inference Launch Engineering
Classified Tasks (27)
Automate 0%Augment 96%Human-Only 4%
Augment (26)
AI assists, human decides
Scale and optimize Claude inference across AWS, GCP, Azure, and other cloud service providers
technical
Own API integration for Claude on each cloud platform
technical
Implement intelligent request routing for Claude across cloud platforms
technical
Operate inference execution on each cloud platform
operational
Manage capacity for inference workloads on cloud platforms
operational
Perform day-to-day operations for Claude deployments on cloud platforms
operational
Design, implement, and own the validation pipeline for the inference server and load balancer across cloud platforms
technical
Validate model launches to ensure correct deployment on cloud platforms
operational
Validate performance improvements before they land on cloud platforms
analytical
Ensure inference changes land on cloud platforms with correctness, performance, and reliability intact
operational
Make validation fast and cost-effective enough to run on the same accelerators that serve customers
technical
Replace manual checks by building trustworthy automated validation
technical
Ensure validation consistency so changes that work on Anthropic first-party also work on CSPs
technical
Bring up inference for new model architectures on cloud platforms
technical
Ship new models to cloud platforms in lockstep with the first-party platform
operational
Integrate new inference features (e.g., structured sampling, prompt caching) into each cloud platform and deploy them to production
technical
Identify configuration drift, observability gaps, deployment pattern differences, and cross-platform bugs causing inference divergence
analytical
Diagnose root causes of cross-platform inference issues through deep investigation
analytical
Fix root causes of cross-platform issues rather than implementing platform-specific workarounds
technical
Design, build, and own CI/CD infrastructure for the inference server and load balancer across cloud platforms
technical
Implement shadow traffic testing for CI/CD validation pipelines
technical
Establish performance baselines (throughput and latency) for inference across cloud platforms
analytical
Implement correctness checks that catch regressions before production
technical
Reduce merge-to-production cycle time by making validation faster, more parallel, and cost-effective while maintaining reliability
operational
Analyze observability data across providers to identify performance bottlenecks, cost anomalies, and regressions
analytical
Drive remediation actions for identified performance bottlenecks, cost anomalies, and regressions based on real-world production workloads
leadership
Human-Only (1)
Requires human judgment
Validate safeguard integrations prior to production deployment on cloud platforms
operational
Job description
About Anthropic Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems. About the Role The Cloud Inference team scales and optimizes Claude to serve the massive audiences of developers and enterprise companies across AWS, GCP, Azure, and future cloud service providers (CSPs). We own the end-to-end product of Claude on each cloud platform, from API integration and intelligent request routing to inference execution, capacity management, and day-to-day operations. Within Cloud Inference, the model & inference launch team owns the validation pipeline for our inference server and load balancer on these platforms. We're responsible for every inference change — model launches, performance improvements, safeguard integrations — landing on cloud platforms with correctness, performance, and reliability intact. This is high-leverage infrastructure work: validation has to be fast and cheap enough to run on the same accelerators that serve customers, trustworthy enough to replace manual checks, and consistent enough that a change working on Anthropic first-party means it works everywhere. This directly determines how fast frontier models and features ship to every cloud platform, and how quickly performance wins reach production — reclaiming capacity at a time when compute is our scarcest resource. What You'll Do Be on the critical path for frontier model launches, bringing up inference for new model architectures and shipping them to cloud platforms in lockstep with our first-party platform Work with the core inference team to bring new inference features (e.g. structured sampling, prompt caching, and more) to cloud platforms, owning the platform-specific integration that gets them to production Identify and dive deep on the gaps that make inference behave differently across first-party and CSPs — config drift, observability, deployment patterns, hard cross-platform bugs — and fix them at the source rather than building platform-specific workarounds Design, build, and own the CI/CD infrastructure for the inference server and load balancer across cloud platforms, with shadow traffic, performance baselines (throughput and latency), and correctness checks that catch regressions before production Drive down merge-to-production cycle time by making validation faster, more parallel, and cost-effective enough to run on the same constrained accelerator pool that serves customers, without trading away reliability Analyze observability data across providers to identify performance bottlenecks, cost anomalies, and regressions, and drive remediation based on real-world production workloads You May Be a Good Fit If You: Have a strong interest in LLM serving; prior inference or ML experience is not required Have significant software engineering experience, with a strong background in high-performance, large-scale distributed systems serving millions of users Have a track record of building automation or test infrastructure that measurably improved release velocity or reliability Have experience building or operating services on at least one major cloud platform (AWS, GCP, or Azure), with exposure to Kubernetes, Infrastructure as Code, or container orchestration Thrive in cross-functional collaboration with both internal teams and external partners Are a fast learner who can quickly ramp up on new technologies, hardware platforms, and provider ecosystems Are highly autonomous and take ownership of problems end-to-end, including work that fa