Staff & Senior Software Engineer, Cloud Inference

Anthropic Limited; San Francisco (CA); Ibrido; USD 320.000 - 485.000; Tempo pieno

Vantaggi offerti da questo lavoro

Competitive compensation

Equity donation matching

Generous vacation and parental leave

Flexible working hours

Nice office space

Descrizione del lavoro

Anthropic is seeking an experienced Cloud Inference Engineer in San Francisco to accelerate frontier models across AWS, GCP, and Azure. You will own the end-to-end inference stack, from model launches to production readiness, with emphasis on reliability, performance, and cost efficiency.

You’ll collaborate with the core inference team to push features to CSPs, build scalable CI/CD for inference servers and load balancers, and drive faster release cycles while ensuring correctness and safety

Competenze

• Strong interest in LLM serving; prior inference or ML experience is not required.
• Significant software engineering experience in large-scale distributed systems serving millions of users.
• Experience building automation or test infrastructure that improves release velocity or reliability.
• Experience operating services on AWS, GCP, or Azure, with exposure to Kubernetes, IaC, or container orchestration.
• Thrives in cross-functional collaboration with internal and external partners.
• Fast learner capable of ramping up on new technologies, hardware platforms, and provider ecosystems.
• Highly autonomous with ownership of problems end-to-end.

Mansioni

• Be on the critical path for frontier model launches, bringing up inference for new model architectures and shipping them to cloud platforms.
• Collaborate with core inference teams to bring new features to cloud platforms and own platform-specific integration to production.
• Identify and fix gaps causing inference behavior differences across CSPs—config drift, observability, deployment patterns—at the source.
• Design, build, and own CI/CD infrastructure for the inference server and load balancer across cloud platforms, with shadow traffic and performance baselines.
• Reduce merge-to-production cycle time by making validation faster, parallel, and cost-effective while maintaining reliability.
• Analyze observability data across providers to spot performance bottlenecks, cost anomalies, and regressions.

Conoscenze

LLM interest

Software engineering

Automation infra

Cloud platforms

Kubernetes/IaC

Cross-functional

Ownership

Formazione

Bachelor’s degree or equivalent

Strumenti

Python

Rust

Kubernetes

Terraform

Docker

Descrizione del lavoro

Anthropic is seeking an experienced Cloud Inference Engineer in San Francisco to accelerate frontier models across AWS, GCP, and Azure. You will own the end-to-end inference stack, from model launches to production readiness, with emphasis on reliability, performance, and cost efficiency.

You’ll collaborate with the core inference team to push features to CSPs, build scalable CI/CD for inference servers and load balancers, and drive faster release cycles while ensuring correctness and safety