Rack System Architect
FuriosaAI is a South Korean AI semiconductor company building energy-efficient inference accelerators, servers, and software for enterprise and cloud AI deployments.
Funding history
Investors
About FuriosaAI
FuriosaAI develops the RNGD AI inference accelerator and NXT RNGD Server, alongside a software toolchain for compiling, optimizing, and deploying LLM and agentic-AI workloads.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will define the physical architecture of next-generation rack-scale AI computing systems. You will set system budgets and interfaces, translate product needs into engineering requirements, evaluate trade-offs, review partner proposals, manage risks, and establish design standards and technical review processes.
Requirements
- Extensive experience in server, data center, AI/HPC, or complex computing system design
- Experience taking complex hardware systems from system definition through production
- Working knowledge of mechanical, power, thermal, and high-speed interconnect disciplines
- Experience working with external design houses, vendors, or CM/ODM partners
- System-level problem-solving and technical decision-making skills
- Excellent English communication skills
Responsibilities
- Define rack-level system architecture for AI accelerator platforms
- Establish and allocate system-level power, thermal, mechanical, volume, and interconnect budgets
- Translate product requirements into quantified engineering requirements
- Define interfaces and ownership boundaries between internal teams and external partners
- Evaluate architecture options and drive system-level trade-offs
- Review external design proposals and ensure alignment with system requirements
- Define technical requirements and SOW inputs for design houses and CM/ODM partners
- Identify system-level risks and drive mitigation plans
- Establish system-level design standards and technical review processes