R&D Principal Software Engineer Software

Front Door Defense; Austin (TX); On-site; USD 127,100 - 226,000; Full time

Benefits offered by this job

Medical, dental, and vision plans

401(K) participation including company matching

Employee Stock Purchase Program

Paid sick leave and vacation time

Job summary

Broadcom is seeking an experienced R&D Principal Software Engineer to develop AI virtualization stack for GPUs, enhancing ESXi server capabilities. This role involves leading initiatives in ML acceleration for diverse hardware environments.

With over 12 years of experience, candidates will implement cutting-edge technologies in a dynamic setting, requiring strong skills in C++ and Python, as well as solid expertise in ML frameworks. The position offers a competitive salary and comprehensive benefits.

Qualifications

• 12+ years of experience with a Bachelor's degree or 10+ years with a Master's degree.
• 5+ years in ML frameworks (PyTorch, JAX) and graph/ML compiler technologies.
• Strong understanding of GPU/XPU development and optimisation techniques.

Responsibilities

• Lead development of the AI Virtualization Stack for ESXi server.
• Implement and optimise ML backends using OpenXLA framework.
• Troubleshoot bugs related to AI/ML acceleration.

Skills

ML framework/runtime development

GPU/XPU backend engineering

C++ programming

Python programming

Problem-solving skills

Version control systems (Git)

Education

Bachelor's degree in Computer Science or related field

Master's degree in relevant field

Job description

R&D Principal Software Engineer

Lead development of AI virtualization stack enabling multi-vendor GPU/XPU support for ESXi

Location: California, United States

Compensation: $127,100 - 226,000 USD / year

Job Tags: Software

About The Role

Broadcom is a global leader in semiconductor and infrastructure software solutions. As part of our commitment to innovation and excellence, our VMware subsidiary is dedicated to shaping the future of virtualization technology. We are seeking talented individuals to join the GPU Virtualization Team, which is responsible for integrating GPUs in the ESXi Operating System and providing acceleration to AI/ML and Graphics applications running inside the Virtual Machines. The GPU Virtualization Team is part of the VMware Cloud Foundation (VCF) Division which enables readily deployable, easily managed solutions with GPUs to unleash the power of heterogeneous computing for modern applications.

Job Summary

We are seeking an experienced Principal Software Engineer who has experience leading initiatives in the past. As a Principal Engineer, you will be focused on developing and integrating our AI Virtualization Stack to provide hardware‑agnostic acceleration for AI/ML workloads on Virtual Machines. This role is critical in enabling multi‑vendor GPU and XPU support using ML compilation technologies.

Responsibilities

• Research, design, and develop the AI Virtualization Stack for our ESXi server product.
• Implement and optimise PyTorch and JAX backends using the OpenXLA framework to ensure high‑performance AI/ML workload execution across GPUs and XPUs.
• Analyse and re‑architect performance‑critical sections of the ML acceleration code, focusing on optimisation techniques for LLM inference such as KV‑caching and FlashAttention.
• Troubleshoot and address bugs related to AI/ML acceleration functionality.
• Deliver software that meets the coding guidelines and quality standards set by the VCF.
• Develop and maintain technical documentation for delivered features.
• Work closely with the larger team, including virtual driver and device team, as well as external GPU/XPU vendors, to provide end‑to‑end support for ML frameworks.
• Stay up‑to‑date with the latest GPU/XPU hardware architecture and AI/ML compiler technologies.

Qualifications

• 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.
• Excellent communication and collaboration skills.
• Experience with version control systems such as Git.
• Ability to thrive in a fast‑paced and dynamic work environment.
• Familiarity with enterprise coding standards and best practices.

Nice to Have

• Experience with inference servers such as vLLM, Triton.
• Experience with low‑level GPU kernel development and writing custom kernels (e.g., CUDA, ROCm, or similar).

Must have legal authorization to work in the US.

Compensation and Benefits

The annual base salary range for this position is $127,100 - $226,000. As a valued member of our team, you'll be eligible for a discretionary annual bonus and the opportunity to receive not only a competitive new‑hire equity grant, but also annual equity awards, connecting your success directly to the company's growth. All subject to relevant plan documents and award agreements.

Broadcom offers a competitive and comprehensive benefits package: Medical, dental and vision plans, 401(K) participation including company matching, Employee Stock Purchase Program (ESPP), Employee Assistance Program (EAP), company paid holidays, paid sick leave and vacation time. The company follows all applicable laws for Paid Family Leave and other leaves of absence.

Broadcom is proud to be an equal opportunity employer. We will consider qualified applicants without regard to race, color, creed, religion, sex, sexual orientation, national origin, citizenship, disability status, medical condition, pregnancy, protected veteran status or any other characteristic protected by federal, state, or local law. We will also consider qualified applicants with arrest and conviction records consistent with local law.

If you are located outside USA, please be sure to fill out a home address as this will be used for future correspondence.