Systems/Rack Architect

Normal Computing

Mountain View (CA)

Hybrid

USD 180,000 - 240,000

Full time

11 days ago

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Benefits offered by this job

Hybrid work model

Job summary

Normal Computing Corp. is seeking a Hardware System Design Architect to lead the system architecture of its AI compute hardware from concept to rack-scale deployment.

You will own system-level simulation and modeling and will define specifications for boards, chassis, interconnects, and power delivery while collaborating with hardware, software, and lab teams. You will translate workloads into system specs, evaluate architectures, and drive bring-up, integration, and qualification.

Qualifications

  • Experience architecting complex compute hardware systems.
  • Experience taking hardware through requirements to production deployment.
  • Degree in Electrical or Computer Engineering or related field.
  • Excellent written and verbal communication skills.

Responsibilities

  • Own path-finding and architecture for compute system from conception to rack-scale deployment; write specs for boards, interfaces, and rack.
  • Translate workload and performance requirements into system specs: accelerators per node, topology, memory capacity, bandwidth; assess power and cost.
  • Own simulations and hardware models behind platform decisions; run what-if scenarios for design validation.
  • Drive board, chassis, power, and physical design; define envelopes for the design.
  • Define scale-up/scale-out fabrics and interconnects; align with physical design and networking performance.
  • Review ODM/JDM and supplier designs; identify gaps and schedule risks early.
  • Define bring-up, integration, validation, and qualification strategy for each platform.

Skills

System architecture
Compute hardware
Simulation & modeling
Boards & chassis
Interconnect & networking
Vendor management
Bring-up & qualification
Communication skills

Education

Electrical Engineering or Computer Engineering

Tools

CFD modelling
Power integrity tools
CAD/EDA tools

Job description

Hybrid: 3 days a week in the office, in Mountain View, New York or London.

Normal's hardware does not look like just another GPU server, so the system around it cannot be copied from one. As our Hardware System Design Architect, you will lead the system architecture design of Normal's AI compute hardware end-to-end, from initial concept to specification, design reviews, integration, and deployment. You will own system level simulation and modeling and you will use this to guide system-level decisions spanning boards, chassis, interconnects, and rack-scale system design, collaborating closely across hardware, software, and other engineering teams to ensure system designs meet performance and workload requirements.

Working closely with our silicon performance modeling team, software, and lab teams, you will define system requirements and specifications, evaluate architectural options, and drive key technical decisions as our hardware platforms evolve. You'll evaluate partner and vendor designs against our requirements, identify technical gaps and schedule risks early, and lead system-level tradeoffs. You'll play a central role in bringing these pieces together into cohesive, high-performance AI compute systems and driving the overall system from architecture through deployment.

What You Will Own
  • System Architecture and Specifications: Own path-finding and architecture for Normal's compute system from conception to rack scale deployment. Write the system, board, interface, and rack specifications that internal teams and partners build against.
  • Workload-to-System Translation: Translate workload and performance requirements into system specifications: accelerators per node, their topology, memory capacity, and bandwidth per node as well as the performance of scale-up and scale-out fabrics. Own system level performance, power, and total cost of ownership and compare candidate architectures with the needs of customers and the offerings of competitors. Partner with internal teams to model and simulate these performance tradeoffs.
  • Simulation and Modeling: Own the simulations and hardware models behind every platform decision. Run what-if scenarios to identify the best designs and validate deployments in simulation. Consider diverse toolsets from CFD of airflow, coolant loops, rack power distribution, as well as network and workload simulation of scale-out traffic, reliability models, and serviceability.
  • Boards, Chassis, Power and Physical Design: Drive board and chassis-level architecture from major component decisions to power delivery, and thermal and mechanical design. Define the physical, electrical, and thermal envelopes of our design.
  • Interconnect and Networking: Define scale-up and scale-out fabrics from PCIe/CXL interfaces, to card-to-card links, NICs, switches, and optical cabling. Link power, signal integrity, and networking performance requirements holistically with the physical design.
  • Partners and Suppliers: Review ODM, JDM and supplier designs against our requirements, surface gaps, and schedule risk early enough to act on and drive issues to resolution.
  • Bring-up and Qualification: Define and own the bring-up, integration, validation, and qualification strategy for each platform including roof-of-concept builds that de-risk new architecture before volume production.
What Makes You a Great Fit
  • Significant experience architecting complex compute hardware systems, spanning server or machine-level designs through rack-scale platforms
  • Experience taking hardware systems from early requirements and architecture through specification, integration, bring-up, validation, and production deployment
  • Degree in Electrical Engineering, Computer Engineering, or a related field
  • Excellent written and interpersonal communication skills
Bonus Points
  • Successfully architected multiple shipping commercial systems
  • Built new performance, electrical, cooling models from scratch
  • Substantial interactions with partners, including finding new partners and suppliers
Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

System Architect Lead
System Architect Lead

Normalcomputing • Mountain View (CA)

On-site
USD 180,000 - 260,000
Mechanical Engineer, Hardware Systems
Mechanical Engineer, Hardware Systems

Digitailor • Palo Alto (CA)

On-site
USD 140,000 - 210,000
Mechanical Engineer, Hardware Systems
Mechanical Engineer, Hardware Systems

Normal Computing Corporation • Palo Alto (CA)

On-site
USD 150,000 - 210,000
ASIC Architect
ASIC Architect

Normal Computing • Mountain View (CA)

Hybrid
USD 180,000 - 240,000
Mechanical Engineer, Hardware Systems
Mechanical Engineer, Hardware Systems

Normal Computing Corp. • Mountain View (CA)

On-site
USD 140,000 - 220,000
Mechanical Engineer, Hardware Systems
Mechanical Engineer, Hardware Systems

Normal Computing Corporation • Mountain View (CA)

On-site
USD 180,000 - 260,000
ASIC Architect
ASIC Architect

Normalcomputing • Mountain View (CA)

On-site
USD 180,000 - 320,000
ASIC Architect
ASIC Architect

Normal Computing Corporation • New York (NY)

Hybrid
USD 200,000 - 320,000
System Architect Lead — AI Compute Hardware
System Architect Lead — AI Compute Hardware

Normalcomputing • Mountain View (CA)

On-site
USD 180,000 - 260,000
Rack-Scale AI Compute Architect
Rack-Scale AI Compute Architect

Normal Computing Corp. • Mountain View (CA)

Hybrid
USD 180,000 - 240,000
Hybrid work model