Intern, Architect - Analysis of AI Workloads & Network Communication Protocols

Ayar Labs • San Jose, CA

4d • Onsite

About The Position

Ayar Labs is seeking a graduate intern to join its architecture team within the Office of the CTO. The intern will deploy inference and agentic workloads on data center clusters and benchmark their performance, while also architecting and developing specifications for network communication protocol stack layers in Ayar Labs' optical engines. Projects will be tailored to the intern’s experience and interests. The intern will be mentored by a senior engineer and work alongside Ayar Labs engineers to contribute to optical I/O technology for AI hardware. The position runs from May to August 2027 and is on-site at the San Jose office. Immigration support is unavailable except for F-1 students; relocation support is not provided.

Requirements

• Be actively pursuing an M.S. or Ph.D. in Computer Engineering, Computer Science, Electrical Engineering, Mathematics, or an equivalent field.
• Have experience deploying AI workloads on different data center platforms and benchmarking performance.
• Be familiar with profiling and instrumentation tools such as Nvidia Nsight / Nsys, GPGPU-Sim, and LLVM-based tooling.
• Have experience with memory semantic fabrics and network communication protocols such as AXI, CHI, UALink, ESUN, 802.3 Ethernet, UCIe, and PCIe.
• Be independent and highly motivated, able to collaborate and work autonomously, manage time effectively, and complete project tasks.

Responsibilities

• Deploy inference and agentic workloads on data center clusters.
• Benchmark the performance of AI workloads.
• Architect and develop specifications for network communication protocol stack layers in Ayar Labs' optical engines.

What This Job Offers

• Career Level: Intern