Systems Tooling Engineer – Member of Technical Staff

About the role

Callosum is building an orchestration layer for heterogeneous AI compute. The Systems Tooling Engineer will own the developer experience, turning low‑level profiling and tracing data into observable, debuggable tools that enable fast experimentation across new accelerators.

Key responsibilities

• Extend profiling and tracing tooling for new accelerators, handling collection, compression, and visualisation of performance data.
• Develop CLI tools and automation wrappers that simplify common workflows such as spinning up inference stacks, launching benchmarks, and managing configurations.
• Convert prototypes of internal tooling into high‑performance, scalable, and accessible commands.
• Build tooling to support multi‑agent serving workflows, including request tracing across agent boundaries, pipeline visualisation, and debugging of complex inference DAGs.
• Create internal libraries and abstractions that let other teams move faster without reinventing shared infrastructure.

Required profile

• Strong software engineering fundamentals with clean APIs, good error handling, sensible defaults, and clear documentation.
• Experience with profiling and tracing systems such as perf, Nsight, or Tracy, and the ability to make trace data actionable.
• Familiarity with observability stacks like Prometheus, Grafana, or OpenTelemetry in varied infrastructure environments.
• Comfortable across the stack—from low‑level trace collection to dashboards and developer‑facing CLI tools.

Required skills

• perf
• Nsight
• Tracy
• Prometheus
• Grafana
• OpenTelemetry
• CLI development
• Automation scripting
• Profiling
• Tracing
• Visualization

What we offer

• Competitive salary based on skills and experience.
• Equity and ownership opportunities.
• Private healthcare.
• Visa sponsorship and relocation benefits.
• On‑site work in our London office with a supportive, inclusive environment.