Edge AI SoC Architect: Next-Gen Energy-Efficient Silicon
OpenAI
Los Angeles (CA)
On-site
USD 130,000 - 170,000
Full time
14 days+
Application generator
Stand out for this role — generate a tailored resume and cover letter in about a minute.
Get past ATS filters
Job summary
OpenAI is seeking a skilled SoC Architect to shape next-generation custom AI silicon for edge deployments in Los Angeles. This role requires experience in SoC architecture, driving execution from concept to delivery, along with collaboration with internal and external partners. The ideal candidate will lead efforts in the design and optimization of high-performance, energy-efficient chips suited for AI/ML workloads, ensuring robust performance for real-world deployment.
Qualifications
Proven experience defining and delivering complex SoC or ASIC architectures from concept to production.
Deep understanding of AI/ML accelerators, edge inference workloads, and energy-efficient compute design.
Strong knowledge of SoC subsystems including CPU/GPU/NPU architectures, memory hierarchies, interconnects, and power management.
Responsibilities
Define the architecture and technical roadmap for custom SoCs targeted for edge applications.
Drive system-level trade-off analysis across compute, memory, interconnect, power, thermal, and cost constraints.
Lead hardware/software co-design efforts to maximize performance per watt and end-to-end system efficiency.
Skills
SoC/ASIC architecture experience
AI/ML accelerators understanding
Cross-functional team leadership
Strong communication skills
Job description
OpenAI is seeking a skilled SoC Architect to shape next-generation custom AI silicon for edge deployments in Los Angeles. This role requires experience in SoC architecture, driving execution from concept to delivery, along with collaboration with internal and external partners. The ideal candidate will lead efforts in the design and optimization of high-performance, energy-efficient chips suited for AI/ML workloads, ensuring robust performance for real-world deployment.