Staff Software Engineer, AI Reliability Engineering

• Keep Claude reliable for everyone who depends on it — AIRE (AI Reliability Engineering) partners with teams across Anthropic to improve reliability across the most critical serving paths. • Cover every hop from the SDK through the network, API layers, serving infrastructure, and accelerators and back. • Zoom out and look at the whole picture — reliability is an emergent phenomenon that transcends any single team's boundaries. • Be based in London with a hybrid policy expecting at least 25% of time in the office.

• Have a strong distributed systems, infrastructure, or reliability background — we're looking for reliability-minded software engineers and SREs. • Be curious and brave — comfortable jumping into unfamiliar systems during an incident and helping drive resolution even without deep expertise yet. • Think holistically about how systems compose and where the seams are. • Build lasting relationships across teams — the engagement model depends on being welcomed as teammates, not outsiders with opinions. • Care about users and feel ownership over outcomes, even for systems you don't own. • Have excellent communication and collaboration skills — you'll be partnering across the entire company. • Bring diverse experience — the team's strength comes from people who've built product stacks, scaled databases, run massive distributed systems, and everything in between.

• Have been an SRE, Production Engineer, or in similar reliability-focused roles on large-scale systems. • Have experience operating large-scale model serving or training infrastructure (1,000+ GPUs). • Have experience with one or more ML hardware accelerators (GPUs, TPUs, Trainium). • Understand ML-specific networking optimisations like RDMA and InfiniBand. • Have expertise in AI-specific observability tools and frameworks. • Have experience with chaos engineering and systematic resilience testing. • Have contributed to open-source infrastructure or ML tooling.

• Develop appropriate Service Level Objectives for large language model serving systems, balancing availability and latency with development velocity. • Design and implement monitoring and observability systems across the token path. • Assist in the design and implementation of high-availability serving infrastructure across multiple regions and cloud providers. • Lead incident response for critical AI services, ensuring rapid recovery, thorough incident reviews, and systematic improvements. • Support the reliability of safeguard model serving — critical for both site reliability and Anthropic's safety commitments.

• Receive competitive compensation between £325,000 and £390,000 GBP annually. • Get visa sponsorship where possible — Anthropic retains an immigration lawyer to support this. • Take generous parental leave. • Enjoy generous vacation and flexible working hours. • Optional equity donation matching. • Get dynamic, cross-cutting exposure to the systems that matter most at Anthropic — few teams offer this breadth.

Anthropic's mission is to create reliable, interpretable, and steerable AI systems. They want AI to be safe and beneficial for users and society as a whole. The team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems. Anthropic is a public benefit corporation offering competitive compensation and benefits.