Staff and Senior Software Engineer (Cloud Inference)

Anthropic; Seattle (WA); On-site; USD 180,000 - 240,000; Full time

Benefits offered by this job

Comprehensive health, dental, and vis​

Job summary

Anthropic is seeking product-minded backend engineers to design, build, and own backend services for Claude across AWS, GCP, and Azure. You will navigate provider differences, optimize cost, and ensure reliability at massive scale while supporting multiple CSP platforms.

You will collaborate across inference, product API, systems, and security teams, implementing CI/CD pipelines and scalable deployment of new model versions to millions of users with robust safety and performance.

Qualifications

• Experience building or operating services on major cloud platforms (AWS, GCP, or Azure), with exposure to Kubernetes, Infrastructure as Code, or container orchestration.
• Significant software engineering experience with high-performance, large-scale distributed systems serving millions of users.
• Proficiency in Python or Rust and ability to ramp on new technologies and provider ecosystems.
• Ability to work autonomously end-to-end and collaborate across cross-functional teams.

Responsibilities

• Design, build, and own backend services and infrastructure that serve Claude across multiple CSPs, accounting for hardware, networking, APIs, and operational differences.
• Work cross-functionally with inference, product API, systems, and security teams, and with CSP partners to stand up the full serving stack on new cloud platforms.
• Build and evolve CI/CD automation systems and deployment pipelines to ship model versions to millions of users with zero regressions.
• Analyze observability data to identify performance bottlenecks and cost anomalies, driving remediation based on production workloads.

Skills

Python

Rust

Kubernetes

Infrastructure as Code

Multi-region deployments

Cost optimization

Cloud platforms experience

Tools

Kubernetes

Terraform

Job description

• 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
• Our engineers are extremely high leverage: we simultaneously drive multiple major revenue streams while optimizing one of Anthropic’s most precious resources: compute
• As we expand to more cloud platforms, the complexity of managing inference efficiently across providers with different hardware, networking stacks, and operational models grows significantly
• We need product-minded backend engineers who can navigate these platform differences, design the services and abstractions that work across providers, and make architectural decisions that keep us reliable and cost-effective at massive scale
• Your work will increase the scale at which our services operate, accelerate our ability to reliably launch new frontier models and innovative features to customers across all platforms, and ensure our LLMs meet rigorous safety, performance, and security standards
• Design, build, and own backend services and infrastructure that serve Claude across multiple CSPs, accounting for differences in compute hardware, networking, APIs, and operational models
• Work cross-functionally with internal inference, product API, systems, and security teams, among others, and with CSP partners to stand up the full serving stack on new cloud platforms, resolve operational issues, and influence provider roadmaps
• Build and evolve CI/CD automation systems, including validation and deployment pipelines, that reliably ship new model versions to millions of users across cloud platforms without regressions
• Design interfaces and tooling abstractions across CSPs that enable cost-effective inference management, scale across providers, and reduce per-platform complexity
• Contribute to capacity planning, autoscaling, and workload routing strategies that match supply with demand and direct requests to the most cost-effective accelerator and region
• Analyze observability data across providers to identify performance bottlenecks, cost anomalies, and regressions, and drive remediation based on real-world production workloads

Benefits

• Comprehensive health, dental, and vision insurance for you and your dependents
• Inclusive fertility benefits via Carrot Fertility
• 22 weeks of paid parental leave
• Flexible paid time off and absence policies
• Mental health support for you and your dependents
• Competitive salary and equity packages
• Optional equity donation matching at a 1:1 ratio, up to 25% of your equity grant
• Retirement plans with competitive matching
• Life and income protection plans
• $500/month flexible wellness and time saver stipend
• Commuter benefits
• Annual education stipend
• Home office stipends
• Relocation support for those moving for Anthropic
• Daily meals and snacks in the office

Thrive in cross-functional collaboration with both internal teams and external partnersHave experience working with external partners to align goals and deliver impactHave 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 orchestrationHave significant software engineering experience, with a strong background in high-performance, large-scale distributed systems serving millions of usersAre curious about LLM serving; prior inference or ML experience is not requiredAre a fast learner who can quickly ramp up on new technologies, hardware platforms, and provider ecosystemsAre highly autonomous and take ownership of problems end-to-end, including work that falls outside your job descriptionWe encourage you to apply even if you do not believe you meet every single qualificationNot all strong candidates will meet every single qualification as listedResearch shows that people who identify as being from underrepresented groups are more prone to experiencing imposter syndrome and doubting the strength of their candidacy, so we urge you not to exclude yourself prematurely and to submit an application if you’re interested in this workProficiency in Python or RustSolid understanding of multi-region deployments, geographic routing, and global traffic managementHands-on experience with capacity management, cost optimization, or resource planning at scale across heterogeneous environmentsDirect experience working with CSPs to scale infrastructure or products across multiple platforms, navigating differences in networking, security, privacy, billing, and managed service offerings