R&D Principal Software Engineer

Broadcom
California, Austin
Workplace: OnsiteFull timeUSD 127,100 - 226,000 annuallyFunction: Software EngineeringExperience: 12+ yearsEducation: bachelorsSkills: ["Communication","Collaboration","Problem-solving","Teamwork"]

Lead design and integration of the AI Virtualization Stack for the ESXi GPU virtualization product, enabling hardware-agnostic acceleration for AI/ML workloads across GPUs and XPUs. Develop and optimize PyTorch and JAX backends with OpenXLA, improve ML acceleration for LLM inference (KV-caching, FlashAttention), troubleshoot issues, and collaborate with VMkernel teams and external GPU/XPU vendors to deliver high-performance, standards-compliant software.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Broadcom
Broadcom
2 months ago

R&D Principal Software Engineer

✓ Verified Job

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

Source: Company careers pageValidated by: Fursa AI
Last checked: 14 days agoStatus: Live

Job Summary

Lead design and integration of the AI Virtualization Stack for the ESXi GPU virtualization product, enabling hardware-agnostic acceleration for AI/ML workloads across GPUs and XPUs. Develop and optimize PyTorch and JAX backends with OpenXLA, improve ML acceleration for LLM inference (KV-caching, FlashAttention), troubleshoot issues, and collaborate with VMkernel teams and external GPU/XPU vendors to deliver high-performance, standards-compliant software.
Location: California, Austin
Workplace: Onsite
Employment Type: Full time
Job Function: Software Engineering

Key Responsibilities

  • •Research, design, and develop the AI Virtualization Stack for the ESXi server product.
  • •Implement and optimize PyTorch and JAX backends using the OpenXLA framework to ensure high-performance AI/ML workload execution across GPUs and XPUs.
  • •Analyze and re-architect performance-critical sections of the ML acceleration code, focusing on optimization techniques for LLM inference such as KV-caching and FlashAttention.
  • •Troubleshoot and address bugs related to AI/ML acceleration functionality.
  • •Develop and maintain technical documentation for delivered features.

Pay and Benefits

Salary: USD 127,100 - 226,000 annually
Equity and Bonus:Equity
Perks:Health InsuranceDentalVision401kEquityEsppEapPaid LeaveHolidays

Key Requirements

  • •Bachelor's degree in Computer Science or related field and 12+ years of related experience or Masters degree and 10+ years of related experience.
  • •5+ years of experience in ML framework/runtime development, GPU/XPU backend engineering.
  • •Strong understanding and direct experience with ML frameworks (PyTorch, JAX) and graph/ML compiler technologies (e.g. OpenXLA).
  • •Experience with C++ and Python programming languages.
  • •Strong problem-solving skills and ability to troubleshoot complex issues.
Experience:12+ yearsAI hardwareGPU virtualizationSemiconductorsVirtualizationAI frameworks
Education:Bachelor's
Skills:CommunicationCollaborationProblem-solvingTeamwork
Languages:English
Tech Stack:C++PythonPyTorchJAXOpenXLAKV-cachingFlashAttentionGitESXiGPUXPU

Eligibility

Work Authorization:Authorization required. Sponsorship not provided.

Company Brief

Broadcom
Designs, develops, and supplies a broad range of semiconductor and infrastructure software solutions for the data center, networking, broadband, wireless, storage, and industrial markets worldwide.
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: Irvine, United States
Founded: 1991
WebsiteLinkedIn