Principal Engineer, Network Protocol Architect

San Jose, CA · On-site$180k – $250k

About this role

Network Protocol Architect
 
Location: San Jose (on-site)
 
Ayar Labs 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, MediaTek 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.

The successful candidate will work with customers and Ayar Labs’ design teams to design co-packaged optical engines for scale-up and scale-out fabrics and extended memory. You are responsible for developing the specification for network/compute protocol stack layers. The candidate will represent Ayar Labs at Standard Setting Organizations (SSOs) and promote Ayar Labs’ co-packaged optics. You will collaborate with the CTO office on pathfinding activities, and product and technology roadmaps.
 

Essential Functions
  • Using Ayar Labs’ co-packaged optics as the foundational technology, work with customers and internal design teams to design co-packaged optical engines for scale-up and scale-out fabrics and extended memory.
  • Translate customer key interconnect specifications into protocol requirements to enable silicon photonic interconnects.
  • Architect and develop the specification of network/compute protocol stack layers (e.g., application, transaction, data link, and physical) in optical engines.
  • Participate on SSO workgroups at UALink, ESUN, OCP, OIF, and IEEE 802.3.
  • Participate in technology evangelization through customer presentations, conference papers, seminar/webinars.

Required Qualifications 
  • B.S. degree in Computer or Electrical Engineering
  • Experience with memory semantic fabrics and networking protocols such as AXI, CHI, UALink, ESUN, Ethernet (e.g., 802.3dj), UCIe, PCI-SIG
  • Experience with architecture and design of AI compute systems such as OCI-MSA
  • Strong programming skills in Python and familiar with AI workflow agents such as Antigravity, Claude, etc.
  • Self-motivated and detail-oriented
  • Can collaborate and work effectively with colleague across teams and projects
  • Excellent written and oral communication skills

Preferred Qualification
  • MS or Ph.D. degree in Computer or Electrical Engineering
  • Experience with AI inference models and system performance analysis (throughput, interactivity, TCO)
  • Experience with network topologies such as mesh, crossbar, folded Clos, TOR, Leaf-Spine, Torus, Dragonfly, and HyperX
  • Experience with Amazon AWS and Google Cloud platforms
 
Salary range:  $180k - $250k


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 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.
 

Company at a glance

Ayar Labs is transforming AI infrastructure by accelerating data movement. Recognizing that the complexity and size of AI models are increasing at a rate that traditional interconnect technology cannot handle, the company has developed the industry’s first optical I/O solution that enables customers to maximize the compute efficiency and performance of growing AI infrastructure, while reducing costs, latency and power consumption. Based on open standards and optimized for both AI training and inference, Ayar Labs’ optical I/O solution is backed by a robust ecosystem that enables it to integrate smoothly into AI systems at scale.

Founded2015
Team Size51-200 employees
WorkspaceOn-site
IndustryComputer Hardware Manufacturing
Location
San Jose, California, United States
LinkedInLinkedIn

Tired of cold applications?

Sign up with Clera and we'll reach out the moment a role actually fits you — no more spraying applications into the void.

Know someone who'd be great for this?