Principal / Senior GPU SW Performance Engineer — Post‑Training

AMD
San Jose
Workplace: HybridFull timeFunction: Education & TrainingEducation: mastersSkills: ["Communication","Collaboration","Ownership","Problem-solving"]

Lead performance engineering for post-training workloads on AMD Instinct GPUs, driving fast, stable, and reproducible training pipelines across kernels, distributed training, and framework integrations. Collaborate with framework, compiler, kernel, and model teams to improve throughput, memory efficiency, and scalability, and optimize multi-GPU/multi-node training while profiling and diagnosing bottlenecks.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
AMD
AMD
4 months ago

Principal / Senior GPU SW Performance Engineer — Post‑Training

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 4 hours agoStatus: Live

Job Summary

Lead performance engineering for post-training workloads on AMD Instinct GPUs, driving fast, stable, and reproducible training pipelines across kernels, distributed training, and framework integrations. Collaborate with framework, compiler, kernel, and model teams to improve throughput, memory efficiency, and scalability, and optimize multi-GPU/multi-node training while profiling and diagnosing bottlenecks.
Location: San Jose
Workplace: Hybrid
Employment Type: Full time
Job Function: Education & Training
Seniority: Sr. Manager level

Key Responsibilities

  • •Lead performance for finetuning and RL training solutions on AMD GPUs.
  • •Improve throughput, memory efficiency, and stability across data, model, and optimizer steps.
  • •Optimize multi-GPU/multi-node training and communication patterns.
  • •Profile, diagnose, and resolve bottlenecks using standard tooling; prevent regressions in CI.
  • •Collaborate with framework, compiler, and model teams to land durable improvements.

Key Requirements

  • •PhD/MS/BS in Computer Science, Computer Engineering, Electrical Engineering, or equivalent
  • •Proven GPU performance engineering for deep learning workloads (ROCm/HIP, Triton, or similar)
  • •Strong Python and C++ skills; comfortable reading/writing kernels when needed
  • •Hands-on experience with distributed systems and multi-GPU training
  • •Experience with PyTorch and distributed training frameworks (torch.distributed, FSDP/ZeRO) and profiling tools
Experience:SemiconductorsHardwareAI hardwareMachine learning
Education:Master's
Skills:CommunicationCollaborationOwnershipProblem-solving
Languages:English
Tech Stack:PythonC++PyTorchROCmHIPTritonDistributed systemsCUDASFT. LoRARL

Company Brief

AMD
Designs and produces semiconductor products including CPUs, GPUs, and adaptive SoCs for consumer, enterprise, and embedded markets, competing across PCs, data centers, and gaming industries.
Industry: Electronics Manufacturing
Company Size: Enterprise (1,001+ employees)
Revenue: USD 1B+
Growth: Public Company
Valuation: Public Company (Market Cap in USD)
Funding: IPO / Publicly Listed
Headquarters: Santa Clara, United States
Founded: 1969
Glassdoor
Glassdoor: 3.9
WebsiteLinkedIn