Description
About the role
Our Inference team is responsible for building and maintaining the critical systems that serve Claude to millions of users worldwide. We bring Claude to life by serving our models via the industry's largest compute-agnostic inference deployments. We are responsible for the entire stack from intelligent request routing to fleet-wide orchestration across diverse AI accelerators.
As a Staff Software Engineer on our Inference team, you will work end to end, identifying and addressing key infrastructure blockers to serve Claude to millions of users while enabling breakthrough AI research. Strong candidates should have familiarity with performance optimization, distributed systems, large-scale service orchestration, and intelligent request routing. Familiarity with LLM inference optimization, batching strategies, and multi-accelerator deployments is highly encouraged but not strictly necessary.
Strong candidates may also have experience with
- High-performance, large-scale distributed systems
- Implementing and deploying machine learning systems at scale
- Load balancing, request routing, or traffic management systems
- LLM inference optimization, batching, and caching strategies
- Kubernetes and cloud infrastructure (AWS, GCP)
- Python or Rust
You may be a good fit if you
- Have significant software engineering experience, particularly with distributed systems
- Are results-oriented, with a bias towards flexibility and impact
- Pick up slack, even if it goes outside your job description
- Want to learn more about machine learning systems and infrastructure
- Thrive in environments where technical excellence directly drives both business results and research breakthroughs
- Care about the societal impacts of your work
Representative projects across the org
- Designing intelligent routing algorithms that optimize request distribution across thousands of accelerators
- Autoscaling our compute fleet to dynamically match supply with demand across production, research, and experimental workloads
- Building production-grade deployment pipelines for releasing new models to millions of users
- Integrating new AI accelerator platforms to maintain our hardware-agnostic competitive advantage
- Contributing to new inference features (e.g., structured sampling, prompt caching)
- Supporting inference for new model architectures
- Analyzing observability data to tune performance based on real-world production workloads
- Managing multi-region deployments and geographic routing for global customers
Deadline to apply
None. Applications will be reviewed on a rolling basis.
Annual compensation range
The annual compensation range for this role is £325,000-£390,000 GBP.
Logistics
- Minimum education: Bachelor’s degree or an equivalent combination of education, training, and/or experience
- Required field of study: A field relevant to the role as demonstrated through coursework, training, or professional experience
- Minimum years of experience: Years of experience required will correlate with the internal job level requirements for the position
- Location-based hybrid policy: Currently, we expect all staff to be in one of our offices at least 25% of the time. However, some roles may require more time in our offices.
- Visa sponsorship: We do sponsor visas! However, we aren't able to successfully sponsor visas for every role and every candidate. But if we make you an offer, we will make every reasonable effort to get you a visa, and we retain an immigration lawyer to help with this.
Why work with us?
We believe that the highest-impact AI research will be big science. At Anthropic we work as a single cohesive team on just a few large-scale research efforts. And we value impact , advancing our long-term goals of steerable, trustworthy AI , rather than work on smaller and more specific puzzles. We view AI research as an empirical science, which has as much in common with physics and biology as with traditional efforts in computer science. We're an extremely collaborative group, and we host frequent research discussions to ensure that we are pursuing the highest-impact work at any given time. As such, we greatly value communication skills.
The easiest way to understand our research directions is to read our recent research. This research continues many of the directions our team worked on prior to Anthropic, including: GPT-3, Circuit-Based Interpretability, Multimodal Neurons, Scaling Laws, AI & Compute, Concrete Problems in AI Safety, and Learning from Human Preferences.
Come work with us!
Anthropic is a public benefit corporation headquartered in San Francisco. We offer competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and a lovely office space in which to collaborate with colleagues.