AI System Performance Architect
- Experience
- 3+ years
- Education
- PhD
Job Details: Job Description: About the Role We are looking for a talented and motivated AI System Performance Architect.
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
- 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 SG
Lang, 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 poi