Intern, Architect - Analysis of AI Workloads & Network Communication Protocols
Term: May to August 2027

Please note:

Position location is on-site in San Jose Office
There is no immigration (except F1) or relocation support for this position
Posting expires upon application threshold

Position Description

Ayar Labs, the global leader in optical I/O chiplets, is harnessing silicon photonics to revolutionize the scaling of AI compute hardware. AyarLabs is shattering AI data bottlenecks by moving data at the speed of light. As pioneers of co-packaged optics (CPO), we are using light instead of electricity to move data faster, further, and with a fraction of the energy needed to fuel the explosive growth of AI models.

Backed by industry giants like NVIDIA, AMD and Intel and manufactured in partnership with the world’s leading semiconductor ecosystem, Ayar Labs’ co-packaged optics solution is key to unleashing next-generation AI scale-up architectures.

Our architecture team is a key contributor in defining the value of optical I/O technology in AI hardware, through pioneering analyses of leading advanced AI models, hardware and resource requirements for training and inference operations, and the performance gains unlocked by optical I/O.

We are looking for a motivated graduate intern to join our architecture team within the Office of the CTO, where you will deploy inference and agentic workloads on data center clusters and benchmark their performance. Furthermore, you will architect and develop the specifications of network communication protocol stack layers in Ayar Labs' optical engines.

The projects are tailored to your experience and interests, and you will be mentored by a senior engineer as you work alongside Ayar Labs engineers to help drive the optical I/O revolution.

Intern Skillset Needed

Experience in deploying AI workloads on different data center platforms and benchmarking performance.
Familiar with profiling and instrumentation tools such as Nvidia Nsight / Nsys, GPGPU-Sim, and LLVM-based tooling.
Experience with memory semantic fabrics and network communication protocols such as AXI, CHI, UALink, ESUN, 802.3 Ethernet, UCIe, and PCIe.
Independent, highly motivated, and able to work collaboratively and autonomously, self-managing time effectively to take project tasks to completion.

Education Requirements

Candidate should be actively pursuing a M.S. or Ph.D. degree in Computer Engineering, Computer Science, Electrical Engineering, Mathematics, or equivalent.

NOTE TO RECRUITERS:
Principals only. We are not accepting resumes from recruiters for this position. Remuneration for recruiting activities is only applicable subject to a signed and executed agreement between the parties. Please don’t send candidates to Ayar Labs, and do not contact our managers.

Ayar Labs is an Affirmative Action/Equal Opportunity Employer and is strongly committed to all policies which will afford equal opportunity employment to all qualified persons without regard to age, sex, national origin, race, color, ethnicity, creed, religion, gender identity, sexual orientation, disability, veteran status, or any other characteristic protected by law. It is the policy of Ayar Labs to provide reasonable accommodation when requested by a qualified applicant or employee with a disability, unless such accommodation would cause an undue hardship. Veterans are more than welcome and encouraged to apply.

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

About the role

Skills

Full job details