SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 320,000 - 485,000 / annual
Anthropic is seeking a Staff Software Engineer to join the Cloud Inference Launch Engineering team. This role is critical to scaling and optimizing Claude across AWS, GCP, Azure, and future cloud service providers.
The Cloud Inference team owns the end-to-end product of Claude on each cloud platform, from API integration and intelligent request routing to inference execution, capacity management, and operations. Within this team, the model & inference launch team owns the validation pipeline for the inference server and load balancer across platforms. You will be responsible for ensuring every inference change—model launches, performance improvements, safeguard integrations—lands on cloud platforms with correctness, performance, and reliability intact.
This is high-leverage infrastructure work. Validation must be fast and cheap enough to run on the same accelerators that serve customers, trustworthy enough to replace manual checks, and consistent enough that changes working on Anthropic's first-party platform work everywhere. This directly determines how quickly frontier models and features ship to every cloud platform and how rapidly performance wins reach production.
Key responsibilities include:
- Being on the critical path for frontier model launches, bringing up inference for new model architectures and shipping them to cloud platforms in lockstep with first-party platform
- Working with the core inference team to bring new inference features (structured sampling, prompt caching, etc.) to cloud platforms, owning platform-specific integration
- Identifying and fixing gaps that make inference behave differently across first-party and CSPs—config drift, observability, deployment patterns, cross-platform bugs—at the source rather than building workarounds
- Designing, building, and owning CI/CD infrastructure for the inference server and load balancer across cloud platforms, with shadow traffic, performance baselines, and correctness checks
- Driving down merge-to-production cycle time by making validation faster, more parallel, and cost-effective without sacrificing reliability
- Analyzing observability data across providers to identify performance bottlenecks, cost anomalies, and regressions, driving remediation based on production workloads
Requirements:
- Strong interest in LLM serving (prior inference or ML experience not required)
- Significant software engineering experience with strong background in high-performance, large-scale distributed systems serving millions of users
- Track record of building automation or test infrastructure that measurably improved release velocity or reliability
- 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
- Ability to thrive in cross-functional collaboration with internal teams and external partners
- Fast learner who can quickly ramp up on new technologies, hardware platforms, and provider ecosystems
- Highly autonomous, taking ownership of problems end-to-end, including work outside job description
- Bachelor's degree or equivalent combination of education, training, and/or experience in a field relevant to the role
Preferred qualifications:
- LLM inference optimization, batching, and caching strategies
- Capacity-constrained scheduling or shared-resource test infrastructure
- Solid understanding of multi-region deployments, request routing, load balancing, global traffic management
- Working with CSP partner teams to scale infrastructure across multiple platforms
- Proficiency in Python or Rust
