Performance Modeling Engineer

Principal Performance Modeling EngineerWe’re working with a semiconductor company designing a new programmable compute architecture for demanding AI workloads.They’re looking for a senior performance-modeling engineer to create the tools that guide architectural decisions before hardware exists. Your work will determine where performance is gained or lost across compute, memory, interconnect and complete AI systems.What you’ll work onBuild analytical and simulation-based performance modelsModel processors, accelerators, memory hierarchies and interconnectsAnalyze transformer inference across single-device and multi-accelerator systemsEvaluate latency, throughput, utilization, energy and cost trade-offsCharacterize workload behavior using traces and representative benchmarksIdentify architectural bottlenecks and propose measurable improvementsPartner with hardware, compiler, runtime and inference teamsCorrelate models against simulation, emulation or silicon as the platform maturesWhat we’re looking forStrong Python and/or C++ developmentExperience building performance modelsDeep computer-architecture and microarchitecture knowledgeUnderstanding of compute pipelines, memory systems and data movementAbility to convert model results into concrete architecture decisionsExperience with GPUs, AI accelerators, LLM inference, cluster modelling, roofline analysis, NoCs or cost-per-token analysis would be especially relevant.This is an architecture-shaping role where performance models influence both the silicon and the software designed around it.