Kandou AI Raises $225M in Series A Funding

2026-04-07 · Source: Big Data & AI News - EE Times · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Cloud Computing & IT Infrastructure, Emerging Technologies & Innovation · Depth: Advanced, medium

Summary

Swiss fabless semiconductor startup Kandou AI has secured $225 million in Series A funding, led by Maverick Silicon with participation from SoftBank Group, Synopsys, Cadence Design Systems, and Alchip Technologies. This capital will scale its high-speed connectivity chips, which aim to resolve data movement bottlenecks in AI systems. The company's technology, based on 14 years of research by CTO Amin Shokrollahi, improves data transmission between memory and compute over copper interconnects by treating crosstalk as usable signal energy rather than noise. Kandou AI has already shipped over 20 million units for data center, AI, and consumer applications, and is expanding its engineering presence. Its core innovation, Copper MIMO or chord signaling, applies information theory to wired interconnects to push copper's limits, offering potential reductions in cost by 12x, scalability and reach by 10x, and power consumption by 3x, without requiring advanced packaging like silicon interposers.

Key takeaway

For CTOs and VPs of Engineering grappling with escalating data movement bottlenecks in AI infrastructure, Kandou AI's $225 million funding and its Copper MIMO technology signal a viable alternative to optical interconnects. Your teams should evaluate this approach for rack-level connectivity beyond 448G, as it promises significant cost, power, and scalability improvements for future private and sovereign AI deployments without requiring advanced packaging.

Key insights

Kandou AI's chord signaling redefines crosstalk as usable signal, boosting copper interconnect capacity for AI.

Principles

• Treat interference as signal, not noise.
• Analog processing reduces power consumption.
• Copper interconnects have untapped capacity.

Method

Kandou AI employs Copper MIMO (chord signaling), applying a transformation at the transmitter and an inverse at the receiver to utilize crosstalk as usable signal energy, implemented via analog vector-matrix multiplication.

In practice

• Reduce AI system interconnect costs by 12x.
• Extend data reach up to 10x.
• Lower power consumption by 3x.

Topics

• Kandou AI
• High-Speed Interconnects
• AI Data Movement
• Copper MIMO
• Analog Circuit Design

Best for: CTO, VP of Engineering/Data, Director of AI/ML, AI Hardware Engineer, AI Architect, Investor

Related on AIssential

• This Will Power Everything — Optical interconnects are critical for scaling AI data centers beyond copper's physical and thermal limitations.
• Nvidia Buys Enterprise Model-Maker Kumo AI for at Least $400 Million — Nvidia's acquisition of Kumo AI for over \$400 million expands its enterprise AI software capabilities.
• UK AI chip startup Fractile raises $220M to tackle the growing inference bottleneck — The inference bottleneck, driven by memory bandwidth, limits frontier AI progress and economic viability.
• AMD Plans $10B Investment in Taiwan to Boost AI Infrastructure — AMD's $10B Taiwan investment and 2-nm EPYC production highlight intense AI infrastructure scaling despite TSMC supply constraints.
• Benchmark raises $225M in special funds to double down on Cerebras — Cerebras' Wafer Scale Engine uses entire silicon wafers for massive parallel processing, accelerating AI inference.
• Orbital Industries secures $50M to scale data centre infrastructure systems — AI accelerates industrial hardware development, enabling faster materials discovery and deployment for high-density computing.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Big Data & AI News - EE Times.