PCIe/CXL Subsystem Architect
South Korean AI semiconductor and infrastructure company building inference accelerators, servers, racks, and software for production-scale AI deployment.
Funding history
Investors
About Rebellions
Rebellions develops purpose-built AI inference hardware and an accompanying software stack. Its current offerings include the Rebel100 accelerator and deployable RebelServer, RebelRack, and RebelPOD systems, designed for energy-efficient data-center inference.
Skills
Candidate Availability
About the Role
You will define the PCIe/CXL subsystem architecture of data center AI accelerator SoCs from a silicon perspective, covering host interface, peer-to-peer connectivity, virtualization and security. You will translate platform requirements into controller, PHY and SoC integration decisions, and work at the intersection of silicon, system software and server platforms. You will also guide design and software engineers through IP evaluation, design, verification and silicon bring-up.
Requirements
- Master's or higher degree in Electrical Engineering, Computer Science, or a related field
- 5+ years of experience in PCIe subsystem architecture or design for data center SoC
- Deep understanding of the PCIe specification (Gen5/Gen6 and beyond) and CXL
- Experience bridging platform-level requirements to silicon architecture decisions
Responsibilities
- Define PCIe/CXL subsystem architecture from a SoC silicon perspective and translate platform requirements (bandwidth, latency, topology) into controller, PHY and interconnect architecture
- Architect host and device interface features, including SR-IOV, ATS/PRI and IDE/TDISP, and integrate them with the SoC MMU, address map and security architecture
- Define how PCIe requirements impact IP selection, link configuration, power management, clocking/reset and interoperability with server platforms, switches and retimers
- Provide architectural guidance during IP evaluation, design, verification and silicon bring-up with design and software engineers
Hiring Process
Document screening > online interview > on-site interview > culture-fit interview > compensation discussion > final acceptance. Process may vary by role.
