AI System Performance Architect

Job Details: Job Description: About the Role We are looking for a talented and motivated AI System Performance Architect. The role owns the end-to-end understanding of AI training and inference systems, sitting where serving strategy, parallelism, collective communication, and interconnect behavior come together. Through analytical modelling and multi-GPU simulation, the candidate translates SLA and deployment targets into concrete architectural guidance for Intel's future AI platforms. Strong analytical skills and the ability to present performance findings and configuration recommendations to engineering and leadership teams are essential. Key Responsibilities • Own end-to-end understanding of the AI training/inference system and build analytical models and multi-GPU simulation - including MPI/collective communication (allgather, allreduce, all-to-all) and interconnect contention - to project performance, expose architectural bottlenecks, and recommend optimal Intel system configurations. • Model inferencing strategies - static batching, continuous batching, disaggregated serving, and chunked prefill - across frameworks such as vLLM and SGLang, covering agentic inferencing, prefix caching, and multi-turn flows. • Cover data, pipeline, tensor, and expert parallelism and their communication patterns. • Drive studies against SLA targets - batch size, TTFT, TPOT, ISL/OSL, and TPS. • Analyse regression run traces and find patterns in utilization counters across SLA operating points to identify architectural bottlenecks. • Perform what-if analysis by sweeping core count, memory/cache capacity and bandwidth, fabric bandwidth, GPU interconnect, and deployment options; deliver optimization and optimal architecture recommendations. • Scout whitepapers, blogs, and conferences; keep self and team updated on AI innovations applicable to Intel's end-to-end system. Qualifications: Required Qualifications • Bachelor's, master's or PhD in Electrical Engineering, Computer Engineering, Computer Science, or a related field. • Bachelors with 8+ yrs, master’s with 6+ years and Ph.D. with 3+ years of experience in system performance modelling, AI workload analysis, or hardware architecture. • Strong proficiency in Python, with the ability to build modular, maintainable analytical models and simulation frameworks. • Solid understanding of LLM inference and training mechanics: prefill vs. decode, KV cache, batching policies, and quantization. • Working knowledge of distributed parallelism strategies and their communication patterns. • Familiarity with multi-GPU interconnect architectures (NVLink, PCIe, CXL, or equivalent). • Understanding of SoC and platform fundamentals: core count scaling, cache/memory capacity and bandwidth, and fabric behavior. Good-to-Have Skills • Experience building discrete-event simulators for multi-node or multi-accelerator systems. • Familiarity with performance profiling tools (e.g., Intel VTune, NVIDIA Nsight, or similar).