Inference Performance & Deployment - Member of Technical Staff

The role

This person will design tooling and methodologies to ground technology in real-world performance and behavior. They will run experiments on heterogeneous infrastructure to characterize performance and drive decisions on production-readiness.

What you will do

• Run experiments self-hosting models on cloud instances or on-prem across providers and hardware configurations
• Develop and maintain deployment patterns optimized for latency, throughput, and cost
• Work at the orchestration and routing software to improve caching, request scheduling, batching, and resource allocation
• Act as the integration point for other roles to provide feedback on bottlenecks and essential capabilities
• Build and maintain benchmarking harnesses, regression suites, and performance dashboards

Required qualifications

• Experience deploying and benchmarking large model inference in production or production-equivalent environments
• Familiarity with multi-node GPU deployments and associated networking/communication stacks
• Strong end-to-end performance characterisation skills
• Familiarity with serving frameworks like Dynamo, Triton Inference Server, or similar orchestration layers
• Clear communication skills
• A demonstrable disciplined and systematic approach to deployment

Benefits

• Competitive Salary
• Equity & Ownership
• Private healthcare
• Visa sponsorship
• Relocation benefits

About the company

Callosum is the Intelligent Systems Company building infrastructure that unifies heterogeneous compute across the full stack. They are engineers and scientists based in London.