Principal Engineer, SoC Architect
About this role
We are seeking a highly experienced Principal Engineer – SoC Architect to define and drive next-generation SoC architectures for high-performance semiconductor products. This role requires deep expertise in system-level architecture, high-speed I/O integration, performance optimization, scalability, and cross-functional technical leadership.
The ideal candidate will play a critical role in shaping SoC platforms from concept through silicon realization, with strong emphasis on high-speed interfaces, subsystem architecture, interoperability, power/performance optimization, and architectural innovation.
- Define end-to-end SoC architecture for complex semiconductor platforms across compute, memory, interconnect, security, and peripheral subsystems.
- Drive architectural tradeoff analysis involving performance, power, area (PPA), latency, scalability, and cost.
- Develop architectural specifications, subsystem partitioning, and top-level integration strategies.
- Collaborate with product, software, firmware, RTL, verification, physical design, and validation teams throughout the development lifecycle.
- Lead architecture and integration of high-speed interfaces including: PCIe, Ethernet, USB, SerDes, CXL/UCIe and other advanced interconnect protocols.
- Define bandwidth, latency, coherency, buffering, QoS, and interoperability requirements.
- Drive system-level performance modeling and interface optimization.
- Partner with PHY, signal integrity, packaging, and board teams to ensure robust end-to-end solutions.
- Develop architectural models, traffic analysis, and workload characterization frameworks.
- Drive power-aware architecture decisions and dynamic performance management strategies.
- Provide architectural leadership across multiple SoC programs and product generations.
- Mentor senior engineers and influence organization-wide architectural methodologies.
- Lead technical reviews, design evaluations, and architecture signoff discussions.
- Drive alignment across hardware, firmware, software, and platform ecosystems.
- Work closely with: Design and verification teams on implementation feasibility, Firmware/software teams on boot, drivers, and runtime optimization, Validation teams on bring-up and debug strategies and Product and business teams on roadmap alignment.
- Interface with external IP vendors and ecosystem partners when required.
- Bachelor’s, Master’s, or PhD in Electrical Engineering, Computer Engineering, or related field.
- 12+ years of experience in SoC/system architecture and semiconductor product development.
- Proven expertise in large-scale SoC architecture definition and subsystem integration.
- Strong understanding of High-speed I/O architectures and protocols, On-chip interconnects and coherency fabrics, Memory subsystem architecture, Performance modeling and analysis and Power/performance optimization techniques.
- Experience with architecture modeling tools, simulation environments, and performance analysis methodologies.
- Strong technical communication and leadership skills.
- Deep expertise in one or more high-speed I/O technologies such as PCIe Gen5/Gen6, CXL, UCIe, HBM, or advanced SerDes architectures.
- Experience with heterogeneous compute architectures involving CPU, GPU, AI/ML accelerators, or DSP subsystems.
- Knowledge of chiplet-based architectures and advanced packaging technologies.
- Experience with silicon bring-up, post-silicon debug, and system validation.
- Familiarity with automotive, AI/ML, datacenter, networking, or mobile SoC platforms.
- Publications, patents, or industry contributions in SoC or high-speed interconnect architecture are a plus.
- Influence long-term SoC technology and platform strategy.
- Drive innovation in scalable and reusable architecture frameworks.
- Champion engineering excellence, design quality, and execution rigor.
- Foster collaboration across globally distributed engineering organizations.
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.
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?