Performance Modeling Architect- Data Center GPU

OverviewWHAT YOU DO AT AMD CHANGES EVERYTHINGWe care deeply about transforming lives with AMD technology to enrich our industry, our communities, and the world. Our mission is to build great products that accelerate next-generation computing experiences - the building blocks for the data center, artificial intelligence, PCs, gaming and embedded. Underpinning our mission is the AMD culture. We push the limits of innovation to solve the world's most important challenges. We strive for execution excellence while being direct, humble, collaborative, and inclusive of diverse perspectives.AMD together we advance_The RoleAs a Fellow/ Sr Fellow level Engineer you will spearhead performance analysis and modeling for AMD datacenter GPUs. You will lead efforts that enable massive model training at scale. Your expertise will lead teams to drive performance gains in both training and inference pipelines through innovative system design and optimization. You will champion adoption of cutting-edge techniques across the engineering organization. This role requires deep understanding of GPU microarchitecture, memory hierarchies, and their impact on large-scale ML workloads.ResponsibilitiesLead performance modeling and optimization for multi-trillion parameter LLM training/inference including Dense, MoE with multiple modalities (text, vision, speech)Model/optimize novel parallelization strategies across tensor, pipeline, context, expert and data parallel dimensionsArchitect memory-efficient training systems utilizing techniques like structured pruning, quantization (MX formats), continuous batching/chunked prefill, speculative decodingIncorporate and extend SOTA models such as GPT-4, Reasoning models (Deepseek-R1), and multi-modal architecturesCollaborate with internal and external stakeholders/ML researchers to disseminate results and iterate at rapid pacePreferred ExperienceDeep experience optimizing large-scale ML systems and GPU architecturesStrong track record of technical leadership in GPU performance and workload analysis including patents and recent publications, participation in industry forums and peer acknowledgementDeep expertise in CUDA programming, GPU memory hierarchies, and hardware-specific optimizationsProven track record architecting distributed training systems handling large scale systemsExpert knowledge of transformer architectures, attention mechanisms, and model parallelism techniquesPreferred Technical CompetenciesPyTorch, CUDA, TensorRT, OpenAI TritonDistributed systems: Ray, Megatron-LMPerformance analysis tools: NSight Compute, nvprof, PyTorch ProfilerKV cache optimization, Flash Attention, Mixture of ExpertsHigh-speed networking: InfiniBand, RDMA, NVLinkAcademic CredentialsBachelors, MS/PhD in Computer Science/Engineering or equivalent industry experienceAMD does not accept unsolicited resumes from headhunters, recruitment agencies, or fee-based recruitment services. AMD and its subsidiaries are equal opportunity, inclusive employers and will consider all applicants without regard to age, ancestry, color, marital status, medical condition, mental or physical disability, national origin, race, religion, political and/or third-party affiliation, sex, pregnancy, sexual orientation, gender identity, military or veteran status, or any other characteristic protected by law. We encourage applications from all qualified candidates and will accommodate applicants/' needs under the respective laws throughout all stages of the recruitment and selection process.Benefits offered are described: AMD benefits at a glance. #J-18808-Ljbffr

Created: 2025-09-21