Intel
Bengaluru, Karnataka, India Posted 5d ago
Intel is looking for an AI System Performance Engineer to build an understanding of AI training and inference systems. You will develop analytical models that project end-to-end system performance and locate architectural bottlenecks.
Key Responsibilities
Enable new AI workloads in analytical simulators and model emerging multi-GPU deployment and parallelization strategies.
Build analytical models of newly proposed GPU architectures and produce performance estimates.
Integrate and modify open-source simulators or analytical models for Intel-specific architecture.
Perform what-if analysis by sweeping core count, memory capacity, and fabric bandwidth to deliver optimization recommendations.
Requirements
BTech or Master's degree in Electrical Engineering, Computer Engineering, Computer Science, or a related field.
College graduate or 1+ years of experience in AI workload and GPU architecture modelling.
Strong proficiency in Python to build modular analytical models and simulation frameworks.
In-depth understanding of computer architecture including GPU/CPU cores, caches, and memory types.
In-depth understanding of LLM AI workloads and kernel internals.
