Inference Performance & Deployment - Member of Technical Staff

About the Company

Callosum is the Intelligent Systems Company. We believe the next era of AI requires heterogeneity at the infrastructure level—diverse models on diverse chips. We co-evolve models, workflows, and silicon together to create systems of capability that move the Pareto frontier of what is possible.

Responsibilities

• 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 on orchestration and routing software to improve caching, request scheduling, batching, and resource allocation
• Act as an integration point for other engineering functions to provide feedback on bottlenecks and stack optimizations
• Build and maintain benchmarking harnesses, regression suites, and performance dashboards

Requirements

• Experience deploying and benchmarking large model inference in production-equivalent environments
• Familiarity with multi-node GPU deployments and networking/communication stacks
• Strong end-to-end performance characterization skills (network, runtime, memory, or model bottlenecks)
• Familiarity with serving frameworks like Triton Inference Server or similar orchestration layers
• Disciplined approach to deployment, reproducibility, and measurement methodology
• Clear communication skills to translate data into actionable feedback

Benefits

• Competitive Salary
• Equity & Ownership
• Private healthcare
• Visa sponsorship and relocation benefits