Remote - United States · 1d ago · New
Chief Architect, GPU Infrastructure & Rack-Scale Systems - Israel
Unconventional AI · posted todayFresh: apply early
Open to candidates in Israel and United States
Principal
Sign up and we score this job against your resume. You never pay to apply.
RemoteHunt reads employers' own pages. Free to browse. How we check
What this job asks for
Extracted by RemoteHuntMust have
- •Architecting GPU infrastructure
- •Rack-scale system design
- •Leading complex hardware platforms
- •Reasoning across abstraction levels
- •Accelerator interconnects, networking, memory, storage
- •High-density power and cooling
- •Technical leadership across organizational boundaries
Nice to have
- •Large-scale AI training and inference infrastructure
- •HBM, DDR, PCIe/
CXL, Ethernet, InfiniBand - •Chiplet architectures, die-to-die connectivity
- •Infrastructure economics, utilization, TCO
Read the full posting
About Unconventional
Since 2022, AI has entered the mainstream, reshaping entire industries from education and software development to fundamental consumer behaviors. This revolution has created an unprecedented demand for computation—a demand that is now fundamentally limited by energy, not just in the datacenter, but at a global scale.
At Unconventional , our mission is to solve this. We are rethinking computing from the ground up to build a new foundation for AI that is 1000x more efficient . We're doing this by exploiting the rich physics of semiconductors, mapping neural networks directly to the device physics rather than relying on layers of inefficient abstraction.
We’re looking for an experienced technical leader to define the architecture of GPU infrastructure across data center, rack, server, chip, and die levels.
This role requires someone who can connect workload requirements to detailed hardware specifications, understand the interactions across the full system, and guide teams toward a coherent solution. You’ll own architectural decisions spanning compute, networking, memory, storage, power, cooling, and management and control.
What you’ll do
- Set the architectural direction for GPU-based infrastructure, translating product and workload requirements into system architectures and hardware specifications.
- Define requirements and interfaces across racks, servers, boards, chips, and dies, working with domain experts to drive implementation.
- Architect scale-up and scale-out connectivity, including accelerator interconnects, host connectivity, and data center networking.
- Define compute, memory, and storage hierarchies based on workload characteristics, bandwidth, latency, capacity, and data movement.
- Establish power delivery, cooling, and physical integration requirements at server and rack levels.
- Define requirements for provisioning, orchestration, telemetry, fault management, serviceability, and system control.
- Lead tradeoffs across performance, power, cost, reliability, scalability, and deployment constraints.
- Align silicon, hardware, networking, firmware, software, and infrastructure teams around a shared architecture and roadmap.
- Lead technical reviews, resolve cross-domain issues, and validate architectural assumptions through modeling, prototypes, and measured results.
What you bring
- Extensive experience architecting data center infrastructure, with deep expertise in GPU or accelerator-based systems and rack-scale design.
- A track record of leading complex hardware platforms from architecture through deployment.
- The ability to reason across abstraction levels—from workload behavior and fleet requirements to chip and die constraints.
- Strong knowledge of accelerator interconnects, networking topologies, memory systems, storage architectures, and their impact on application performance.
- Experience with high-density power and cooling, system management, reliability, and operational requirements.
- Proven technical leadership across organizational boundaries, with the judgment to make difficult tradeoffs and the clarity to explain them.
- The ability to turn broad goals into precise, actionable specifications and guide teams through execution.
Additional relevant experience
- Large-scale AI training and inference infrastructure.
- HBM, DDR, PCIe/CXL, high-speed Ethernet, InfiniBand, and accelerator fabrics.
- Chiplet architectures, die-to-die connectivity, and advanced packaging.
- Infrastructure economics, utilization, and total cost of ownership
Why Join Us?
- The Mission: Redefine computing for the next 50 years by solving the fundamental energy limitation of AI at a global scale.
- The Impact: Shape the company's future as a foundational team member. Enjoy massive ownership and an outsized opportunity to drive change.
- The Challenge: Dive into deeply complex, intellectually stimulating, and unsolved problems at the cutting edge of multiple, converging fields.
- The Perks: A comprehensive package including best-in-class health benefits, 401k matching, truly unlimited PTO, and complimentary meals in our Mountain View office.
More remote jobs
United States - Remote · 5d ago
United States (Remote) · 6d ago
Remote within the Continental United States · 18d ago
Principal Engineer, Stack
Parallelwireless
US (Remote) · 20d ago
Remote, Canada; Remote, United States · 29d ago
Get new jobs like this by email
Once a week. Remote software engineer jobs that can hire you in your country.
See how well this job fits your resume
Free, no card.
See my match for each job — free