Staff Software Engineer - Observability & Fleet Profiling

anthropic; Greater London; On-site; GBP 100,000 - 140,000; Full time

Job summary

United States Digital Space LLC is seeking Software Engineers to join our Observability team within the Infrastructure organization. The role focuses on monitoring and telemetry infrastructure including metrics, logs, traces, and dashboards to ensure reliability of research and product systems.

As we scale GPU/TPU/Trainium clusters, you will build high-throughput telemetry pipelines, profiling, eBPF tracing, and diagnostic tools to help engineers detect and resolve issues quickly, even across

Qualifications

• Hands-on experience building and operating large-scale observability or monitoring infrastructure.
• Experience with end-to-end observability signals from instrumentation to query and analysis.
• Understanding of high-throughput telemetry pipelines and data storage at scale.
• Comfort digging into kernel, network stack, or hardware.
• Strong communication and collaboration across teams.

Responsibilities

• Design scalable telemetry ingest and storage pipelines for metrics, logs, traces, and error data across multi-cluster infrastructure.
• Build observability solutions that provide low-overhead visibility into system behavior across fleets.
• Own and evolve observability platforms, driving migrations and architectural improvements.
• Develop instrumentation libraries, SDKs, and eBPF-based auto-instrumentation.
• Reduce mean time to detection via cross-signal correlation and unified query interfaces.

Skills

Observability infrastructure

Telemetry pipelines

eBPF

Kernel/network expertise

Diagnostics tooling

Communication skills

Independent work

Tools

eBPF

SDKs

Job description

United States Digital Space LLC is seeking Software Engineers to join our Observability team within the Infrastructure organization. The role focuses on monitoring and telemetry infrastructure including metrics, logs, traces, and dashboards to ensure reliability of research and product systems.

As we scale GPU/TPU/Trainium clusters, you will build high-throughput telemetry pipelines, profiling, eBPF tracing, and diagnostic tools to help engineers detect and resolve issues quickly, even across