Inference Performance & Deployment – Member of Technical Staff

About the role

Callosum is building infrastructure that unifies heterogeneous compute across the full AI stack. This role bridges internal engineering and real‑world performance, designing tooling and methodologies to ground technology in production‑equivalent conditions. You will run experiments, characterise performance, and ensure every layer of the stack is guided by empirical evidence.

Key responsibilities

• Run experiments self‑hosting models on cloud instances or on‑prem across providers and hardware configurations, systematically characterising performance envelopes.
• Develop and maintain reproducible, measurable deployment patterns optimised for latency, throughput and cost.
• Improve orchestration and routing software above the inference engine to enhance caching, request scheduling, batching and resource allocation.
• Integrate new accelerator support, engine features and infrastructure upgrades, providing high‑quality feedback on bottlenecks and guiding stack optimisations.
• Build and maintain benchmarking harnesses, regression suites and performance dashboards for shared system health visibility.

Required profile

• Experience deploying and benchmarking large‑model inference in production‑like environments.
• Familiarity with multi‑node GPU deployments and associated networking/communication stacks.
• Strong end‑to‑end performance characterisation skills to isolate bottlenecks in network, runtime, memory or model.
• Ability to communicate performance data clearly and translate it into actionable feedback.
• Disciplined, systematic approach to reproducible measurement and controlled comparisons.

Required skills

• Large‑model inference deployment and benchmarking.
• Multi‑node GPU deployment.
• Performance bottleneck analysis (network, runtime, memory, model).
• Serving frameworks such as Dynamo or Triton Inference Server.

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 full tooling and setup.
• Inclusive workplace with equal opportunity commitment.