Eridu
Company Information
Headquarters
Saratoga, California, USA
Year Founded
2024
Industries
Semiconductors, Computer Networking, Data Centers, Cloud Computing, AI Infrastructure, High-Performance Computing, Telecommunications
What Is Eridu?
Eridu is an AI infrastructure and semiconductor company developing high-performance networking technology for large-scale artificial intelligence data centers. The company designs networking hardware, custom silicon, and supporting software to improve communication between GPUs and other computing systems.
Its technology focuses on AI networking and data center interconnects, addressing the growing demand for faster data movement during AI model training and inference. Eridu develops networking architectures designed specifically for AI workloads rather than adapting conventional enterprise networking equipment.
What Does Eridu Do?
Eridu develops networking systems that help AI data centers transfer information between large numbers of GPUs more efficiently.
AI training and inference workloads require processors to exchange substantial amounts of data. When network connections cannot keep up with computing performance, GPUs may spend time waiting for information instead of processing it.
Eridu addresses this problem by developing AI-optimized network switches and custom networking silicon that increase data throughput while reducing communication delays.
Its systems are designed to simplify data center networking by reducing the number of switches and intermediate connections required to connect large GPU clusters.
The company’s technology targets hyperscale cloud providers, AI research laboratories, and specialized AI computing operators that need to support increasingly large computing environments.
Eridu Technology
Eridu develops custom networking silicon, high-performance switching systems, and advanced interconnect architectures designed for AI computing environments.
Traditional data center networks use multiple layers of switches to move information between servers. In large AI clusters, this arrangement can introduce communication delays, increase power consumption, and require substantial numbers of cables, optical transceivers, and networking devices.
Eridu takes a different approach by designing its networking technology across semiconductor chips, advanced packaging, optical components, hardware systems, and software.
Its architecture incorporates more networking functionality directly into custom silicon, reducing the need for multiple intermediate switching stages.
A central capability is high-radix switching, which allows a network switch to connect a larger number of devices or network links. Higher radix can simplify network topologies and reduce the number of switching layers required for large GPU clusters.
Eridu’s technology supports both scale-up networking, which connects accelerators into tightly coordinated computing groups, and scale-out networking, which connects larger numbers of computing systems across data center infrastructure.
The company has described architectures supporting single-hop scale-up connections involving thousands of GPUs and scale-out networks designed for much larger clusters.
Eridu reports that its proposed architecture could reduce networking equipment requirements, capital costs, and power consumption compared with conventional multi-tier designs. These figures represent company-reported design projections rather than independently verified production results.
Why Eridu Matters
The expansion of artificial intelligence infrastructure is creating new demands on data center networking. Although GPU processing capabilities continue to increase, moving information between processors can limit the performance of large AI systems.
Eridu addresses this challenge through networking hardware designed specifically for AI workloads, rather than relying on incremental improvements to conventional switching equipment.
Its approach could help data center operators improve GPU utilization, reduce communication delays, and lower the infrastructure required to support large computing clusters.
The company is also relevant to the growing market for custom AI semiconductors and advanced data center interconnects, where networking performance is becoming increasingly important alongside computing power.
In March 2026, Eridu emerged from stealth with more than $200 million in announced funding, reflecting investor interest in infrastructure technologies that address AI computing bottlenecks.
Eridu Products & Platforms
Eridu AI Networking Switch
Eridu is developing a high-performance network switch designed specifically for AI data centers. The system combines custom networking silicon, advanced semiconductor packaging, optical technologies, and supporting software.
Its architecture is designed to connect large GPU clusters while reducing the number of intermediate switches and network connections.
Eridu reports that its proposed design can deliver substantial improvements in network throughput, connection density, and energy efficiency compared with conventional multi-tier architectures.
Eridu AI Interconnect Architecture
Eridu’s networking architecture supports scale-up and scale-out connectivity for large AI computing environments.
The design enables thousands of GPUs to communicate through a single-hop scale-up network and supports larger computing clusters through simplified scale-out configurations.
By reducing network tiers, the architecture is designed to lower latency, improve GPU utilization, and reduce the hardware and power requirements associated with AI data center networking.
Eridu Applications
Eridu’s technology is designed for computing environments that require high-bandwidth communication between large numbers of processors.
In hyperscale AI data centers, its networking systems can connect GPU clusters used for training and operating large artificial intelligence models.
For AI research laboratories, the technology can support distributed training workloads where processors must exchange information continuously.
Cloud infrastructure providers and specialized AI computing operators can use high-performance networking to support GPU-based computing services.
Eridu’s architecture is also relevant to high-performance computing, where large groups of processors need low-latency connections for complex computational tasks.
Additional applications include enterprise AI infrastructure and sovereign cloud environments that require scalable computing networks. These are target applications; publicly verified production deployments have not been established.
Latest Companies
Frequently Asked Questions
What is the AI network wall that Eridu addresses?
The AI network wall refers to limitations in the networking infrastructure connecting GPUs and other AI processors. When network bandwidth and latency cannot keep pace with computing requirements, processors spend time waiting for data, reducing the overall performance of AI systems.
What is the difference between scale-up and scale-out networking?
Scale-up networking connects processors within tightly coordinated computing groups that require very fast communication. Scale-out networking connects larger numbers of servers or computing groups across a data center. Eridu is developing networking technology designed to support both configurations.
How could Eridu reduce AI data center networking costs?
Eridu’s architecture is designed to reduce the number of switches, cables, and optical connections needed in large GPU clusters. The company estimates that certain configurations could achieve up to 40% lower capital costs and 70% lower networking power consumption. These are company projections, not independently established results.
Does Eridu manufacture GPUs?
No. Eridu focuses on networking technology that connects GPUs and other AI processors. Its systems are designed to improve communication between computing devices rather than replace the processors responsible for AI calculations.
Is Eridu's AI networking technology commercially available?
Eridu publicly introduced its networking architecture in March 2026 and stated that its funding would support completion of product development. The company has not publicly confirmed general commercial availability or a production deployment schedule.
Do You Have an Update for This Company?
Have an update, correction, or additional information about this company? Help us keep the futureTEKnow company database up to date by submitting the latest company information.
Related Companies
- Enfabrica
- Ayar Labs
- Celestial AI
Latest Articles
OpenAI Astra for Law Brings GPT-6 Astra Into Legal Research and Law Firm Workflows
OpenAI’s Astra for Law combines GPT-6 Astra with specialized legal search, integrations, and governance controls. The launch shows how frontier AI is moving deeper into professional legal workflows.
Are your AI projects stuck on your own data?
AI projects often stall because business data isn’t consistent or trustworthy. Here’s how to identify data gaps before they become an AI roadblock.
EVAS Intelligence’s RISC-V AI Chips Land 1.5 Billion Yuan Series B to Power Global Expansion
EVAS Intelligence has raised 1.5 billion yuan to mass‑produce its RISC-V Epoch AI chips, deepen its full‑stack platform, and accelerate global expansion, signaling rising investor confidence in alternative AI compute.
Orkes Raises $60M to Orchestrate Enterprise AI Agents in Production
Orkes has raised 60 million dollars to turn its Netflix‑born workflow engine into a control plane for enterprise AI agents. The piece unpacks how its orchestration platform works, why investors are backing it now, and what this means for companies trying to move AI from pilots into production.
Sillage’s AI signal engine raises €1.7M to help enterprise sales teams follow the right buying signals
Paris-based Sillage has raised €1.7 million to launch an AI signal engine that helps enterprise sales teams follow the right buying signals, prioritize high-intent accounts, and improve pipeline efficiency without replacing human-led conversations.
Cloneable’s agentic AI platform targets the infrastructure knowledge gap with $4.6M seed round
Cloneable is launching an agentic AI platform for infrastructure operations that captures institutional knowledge from retiring experts and turns it into scalable agents, targeting energy, utilities, and other asset-heavy sectors. The $4.6M seed-backed startup aims to connect field data capture with back-office execution so founders and operators can modernize infrastructure faster and with fewer bottlenecks.
Ricursive Superintelligence’s $500M bet on self-improving AI raises the stakes in the AGI funding race
Excerpt: Ricursive Superintelligence has raised at least $500 million to build self‑improving AI, with GV and Nvidia backing a four‑month‑old lab at a $4 billion valuation. The deal crystallizes how quickly capital, talent and regulatory scrutiny are converging around autonomous AI research—and what that means for builders trying to compete outside the frontier club.
Bond AI raises US$2M to automate SME accounting in Brazil’s brutal tax maze
Brazilian startup BOND has raised US$2M to automate accounting for SMEs in Brazil’s complex tax system. Combining AI with human accountants, it targets a fragmented market of manual processes, aiming to turn back-office compliance into a faster, more strategic function for founders and operators.
Loop’s AI supply chain platform raises $95M Series C to predict disruptions before they hit
Loop just raised a $95M Series C to expand its AI-native supply chain platform, turning messy logistics data into early disruption warnings and better financial outcomes for global operators and shippers.
London AI startup Lua wants to give every business its own AI workforce with $5.8M seed round
Linkedin X-twitter-square Facebook-square Startups & Business News AI agents are finally moving from demos to the day-to-day stack of real
Factory.ai raises $150M Series C to build fully autonomous software engineering “factories”
Factory has raised a $150M Series C at a $1.5B valuation to scale its autonomous “Droids” platform, betting that enterprises will standardize software engineering around agent‑native missions, governance and cost‑optimized AI infrastructure.
Solidroad’s $25M bet on AI quality assurance for customer support
Solidroad has raised $25 million to bring AI-native quality assurance to every human and AI-powered customer interaction. The new funding will accelerate product development and expansion for support-heavy businesses leaning into automation.
futureTEKnow is focused on identifying and promoting creators, disruptors and innovators, and serving as a vital resource for those interested in the latest advancements in technology.
© 2026 All Rights Reserved.