GPU Architecture and AI Performance Simulation Engineer
Intel Corporation (company site, opens in a new tab)10+ yrsBengaluruOn-siteDirect career pageEst. 45–85 LPA
Posted 13h ago
Reach people at Intel Corporation
People at this company you can reach
Log in to see who works here
Create a free account or log in to see the people at Intel Corporation you could write to:
- Recruiters & HR
- People in this function
- Work addresses
Your match
Against your primary resume
Log in to see your match score
Create a free account or log in to unlock your CV match score across:
- Role fit
- Experience
- Industry relevance
Protocol Intelligence
How competitive this role is
Competition
Background fit
Strictness
Log in to see why each signal reads the way it does.
Job description
Structured overview of role & requirements
About This Role
- Analyze and model AI workload performance on GPU and SoC architectures to identify bottlenecks and optimize hardware utilization.
- Develop and maintain analytical and cycle-accurate performance models to guide micro-architectural decisions and early architecture definition of AI GPU accelerators.
- Lead and mentor team members in delivering consistent workload and system-level performance analyses and track AI GPU market trends to inform Intel’s accelerator roadmap.
Minimum Requirements
- Bachelor's degree with 10+ years, Master’s degree with 8+ years, or Ph.D. with 5+ years in System/GPU/SoC performance engineering, AI workload analysis, or hardware architecture.
- Deep knowledge of GPU microarchitecture (e.g., NVIDIA SM/CUDA cores, Intel Xe cores), GPU execution pipelines, and cache hierarchy design (L1/L2/L3).
- Familiarity with SoC design, on-chip fabric, memory subsystems, interconnects, and multi-GPU system architectures such as NVLink, PCIe, or CXL.
- Work Experience Required: Minimum 5 to 10+ years depending on highest degree held.
Ideal Candidate Profile
- Experienced in analyzing and optimizing AI workloads using detailed performance models, including Transformer and MoE architectures for both training and inference.
- Proficient in distributed training/inference methodologies and multi-GPU system scaling with strong understanding of parallelism techniques (Tensor, Data, Pipeline, Expert, Model Split).
- Ability to propose data-backed architectural enhancements and effectively communicate performance trade-offs to engineering and leadership teams.