AI Compute Infrastructure Software Engineer

Summary

Celestica is looking for talented and passionate Senior Staff/Architects for the Hardware Platform Services team. This team is responsible for designing and developing Cloud Hardware infrastructure that includes Compute, Storage, AI servers and Networking Switches. As a Software Engineer, you will play a key role in defining and delivering state of the art Cloud Hardware products.

Detailed Description

This role connects the high-level AI/ML framework behavior with the design of low-level compute Infrastructure firmware components

• Gather Requirements and provide technical solutions that span across the system
• Design, Develop, Augment and maintain drivers, application software, Software libraries that drive next generation CPU and GPU systems for Data Centers
• Review and maintain the quality of code going into production.
• Mentor and coach team members on the technical skills and approaches to solve problems.

Required qualifications:

• Bachelor’s Degree or higher education in Engineering
• Overall 15+ years of experience
• 8+ years of experience in C / C++ and other low-level programming languages and embedded systems
• 8+ years of experience in Hardware bring-up, validation of all low-level interactions, troubleshooting and resolution of hardware / software interfaces
• Working knowledge in at least two or more of the following
• Linux Kernel, BMC, Secure Boot, RDMA, CXL etc.
• A few years of working knowledge with AI/ML workloads, GPU libraries like CUDA and ROCm
• Strong analytical and problem-solving abilities
• Proven ability to articulate requirements and solutions to diverse audiences through written documents like architecture specifications and verbal presentations in technical forums.

Preferred qualifications:

• Familiarity with main elements of CPU, GPU, DPU, memory, NICs
• 15+ years of overall experience