Sr. Software Engineer, Inference

Sr. Software Engineer, Inference Overview

The inference engineering team builds and runs the systems that make Claude available to millions of people around the world. This group owns the infrastructure that serves the models at very large scale, with responsibility spanning the entire path from intelligent traffic handling to orchestration across a diverse fleet of AI accelerators. The work is central to both product growth and research progress: the team must keep compute usage efficient enough to support rapidly expanding demand while also providing the high-performance infrastructure researchers need to develop the next generation of models.

What you would work on

• Designing and operating the core systems that deliver model responses reliably to a global audience.
• Building the full inference stack, including request routing, fleet orchestration, and coordination across different accelerator families.
• Improving compute efficiency so the platform can scale with customer growth.
• Supporting research by providing fast, dependable inference infrastructure for experimentation and model development.
• Solving complex distributed-systems problems in environments that span multiple accelerator types and multiple cloud providers.
• Creating routing strategies that intelligently distribute requests across thousands of accelerators.
• Autoscaling compute resources so supply matches demand across production, research, and experimental workloads.
• Developing deployment pipelines that safely release new models to a very large user base.
• Adding support for new AI accelerator hardware to preserve hardware flexibility and competitive advantage.
• Shipping new inference features such as structured sampling and prompt caching.
• Helping inference support new model architectures as they are introduced.
• Using production observability data to diagnose issues and tune performance based on actual workload patterns.
• Managing multi-region deployments and geographic routing for customers in different parts of the world.

Experience and qualifications

• Significant software engineering experience is expected, especially in distributed systems.
• Background in high-performance, large-scale distributed systems or large-scale machine learning systems would be highly relevant.
• Experience with load balancing, request routing, or traffic management systems would be beneficial.
• Experience improving large language model inference through batching, caching, or related optimization techniques would be a plus.
• Familiarity with Kubernetes and cloud infrastructure such as AWS or GCP would be valuable.
• Ability to work in Python or Rust is considered a strong advantage.
• A bachelor’s degree, or an equivalent combination of education, training, and experience, is required.
• Your studies, training, or professional background should be in a field relevant to the role.
• The exact experience level depends on the internal level assigned to the position.
• You should be comfortable working with flexibility and stepping in wherever needed to create impact.
• A results-focused mindset is important, along with a willingness to take on work beyond a narrow job description.
• You should be interested in learning more about machine learning systems and infrastructure.
• The role is best suited to people who thrive when technical excellence directly influences business outcomes and research breakthroughs.
• Interest in the social and ethical implications of AI is important.
• Strong communication skills matter because the team works collaboratively and regularly discusses research direction.
• Candidates are encouraged to apply even if they do not satisfy every listed qualification.

Team and company context

The broader organization is focused on building reliable, interpretable, and steerable AI systems that are safe and beneficial for users and society. The company describes itself as a fast-growing group of researchers, engineers, policy specialists, and business leaders working together on beneficial AI.

The team culture emphasizes collaboration, frequent research discussion, and a focus on high-impact work rather than small isolated problems. The company says it treats AI research as an empirical science and values communication highly. It also points to prior research directions such as GPT-3, circuit-based interpretability, multimodal neurons, scaling laws, AI and compute, concrete problems in AI safety, and learning from human preferences as part of the intellectual lineage behind its work.

Compensation and benefits

• Annual base salary range of £225,000 to £325,000 GBP.
• Optional equity donation matching.
• Generous vacation allowance.
• Generous parental leave.
• Flexible working hours.
• A pleasant office space designed for collaboration with colleagues.

Working arrangement

This is a hybrid role. Staff are currently expected to spend at least 25% of their time in one of the company’s offices, and some positions may require more in-office presence. The application also asks whether you are open to working in person at that level and whether you are willing to relocate if needed.

Visa sponsorship

The company states that it does sponsor visas. It adds that sponsorship is not possible for every role or every applicant, but if an offer is extended they will make every reasonable effort to secure work authorization and will involve an immigration lawyer to help.

How to apply

Applications are reviewed on a rolling basis, and there is no fixed deadline. The application form requests your name, contact details, resume or CV, and optionally a cover letter. It also asks for your LinkedIn profile or resume, with at least one required. Additional questions cover your preferred pronunciation of your name, your earliest start date, any timing constraints, your understanding of the company’s AI-use policy for applicants, whether you have interviewed there before, why you want to work there, whether you need visa sponsorship, whether you will need employment visa sponsorship now or in the future, whether you are open to relocation, your planned work address or a note that you are relocating, your years of full-time professional software engineering experience excluding internships and co-ops, and the programming language you would choose for a coding interview. The company notes that its coding interviews are practical and are not based on LeetCode-style puzzles. Applicants may also add a cover letter or other information they want to share.

Additional notes

The company warns applicants to watch for scams and says its recruiters use only @anthropic.com email addresses. In some cases, vetted recruiting agencies may contact candidates on the company’s behalf, but they should identify themselves clearly. The company says legitimate recruiters will never ask for money, fees, or banking details before the first day of work. If there is any doubt about a message, candidates are directed to the company careers site to verify openings.

The company also notes that it is a public benefit corporation headquartered in San Francisco.

Degree Requirement: Not Specified

Visa Sponsorship Promising