ML Systems Engineer — LLM Inference Benchmarks

CommonAI CIC is seeking a researcher to build reproducible LLM workloads and benchmarks that reflect real-world use cases. You will collaborate with measurement and simulation engineers to connect workloads to physical measurements and the SIL platform, focusing on long-context and agentic workloads.

You will design and evaluate benchmark suites, specify performance measures, and ensure reproducible comparisons across different hardware and configurations.