Akamai has introduced the Akamai Inference Cloud, the first platform to take AI inference from core data centers to the edge while maintaining low latency and performance, thereby supporting real-time AI handling across the globe.
Akamai’s unique combination of distributed architecture and NVIDIA’s Blackwell AI Infrastructure allows for next-generation AI systems such as personal experiences, smart agents, and real-time decision systems.
Akamai Inference Cloud puts AI inference closer to end-users, enabling real-time, scalable, and secure decision-making in various fields, including fraud detection, industrial robots, and autonomous vehicles.
It integrates NVIDIA RTX PRO Servers, BlueField DPUs, and AI Enterprise software into Akamai’s global edge network, spanning over 4,200 locations.
“The next wave of AI requires the same proximity to users that allowed the internet to scale to become the pervasive global platform that it is today,” stated Dr. Tom Leighton, Akamai CEO and co-founder. “Akamai solved this challenge before and we’re doing it again. Powered by NVIDIA AI infrastructure, Akamai Inference Cloud will meet the intensifying demand to scale AI inference capacity and performance by putting AI’s decision-making in thousands of locations around the world, enabling faster, smarter, and more secure responses.”
The platform enables decentralization of data processing through “AI Factories,” empowering smart agents to learn from user interactions and execute real-time transactions.
It caters to both agentic and physical AI for millisecond-level operations, such as industrial automation and transport, requiring immediate responses.
Akamai Inference Cloud streamlines AI workload processing by directing tasks to the most suitable location for decision-making and workload processing.
The platform is currently accessible in 20 global locations, with expansion plans to meet the rising demand for AI.
Related
AI at the edge | AI cloud infrastructure | AI/ML | Akamai | Nvidia blackwell
