Akamai and NVIDIA redefine AI with Inference Cloud from Core to Edge

Akamai Technologies launched Akamai Inference Cloud, a platform that transforms how and where AI inference is executed by expanding intelligence from core data centres to the edge of the internet.

Purpose-built for agentic and physical AI, the Akamai Inference Cloud delivers low-latency, secure, and scalable inference close to users and devices. Leveraging Akamai’s global edge network, spanning over 4,200 locations, and NVIDIA’s Blackwell AI infrastructure, the platform provides real-time, distributed AI processing designed for the next wave of smart, autonomous systems.

“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,” said Dr. Tom Leighton, CEO and co-founder, Akamai Technologies. “Powered by NVIDIA AI infrastructure, Akamai Inference Cloud will meet the intensifying demand to scale inference capacity and performance by putting AI’s decision-making in thousands of locations worldwide, enabling faster, smarter, and more secure responses.”

Jensen Huang, founder and CEO, NVIDIA, added, “Inference has become the most compute-intensive phase of AI, demanding real-time reasoning at planetary scale. Together, NVIDIA and Akamai are moving inference closer to users everywhere, delivering faster, more scalable generative AI and unlocking the next generation of intelligent applications.”

Key Innovations Driving Akamai Inference Cloud

1. Extending AI Factories to the Edge:

Akamai Inference Cloud decentralises AI processing by extending enterprise AI Factories to the edge. This enables smart commerce agents and personalised digital experiences that respond instantly to user location, behaviour, and intent.

2. Enabling Streaming Inference for Agentic AI:

AI agents require multiple sequential inference calls to complete tasks such as fraud detection or financial insights. Akamai’s edge-native architecture minimises latency, ensuring human-like responsiveness across complex workflows and real-time decision-making.

3. Powering Real-Time Physical AI:

Physical AI systems, autonomous vehicles, industrial robots, and smart city infrastructure demand millisecond-level decision-making. Akamai Inference Cloud processes sensor data and executes safety-critical actions with unprecedented responsiveness, enabling intelligent physical systems that safely operate alongside humans.

4. Accelerating Time-to-Value:

Through its intelligent orchestration layer, the platform dynamically routes inference workloads to optimal locations, whether instantly at the edge through NVIDIA NIM microservices or centrally within AI factories, simplifying distributed AI deployment and maximising efficiency.

Technology Stack and Global Reach

Akamai Inference Cloud integrates NVIDIA RTX PRO Servers with RTX PRO 6000 Blackwell Server Edition GPUs, NVIDIA BlueField-3 DPUs, and NVIDIA AI Enterprise software within Akamai’s global infrastructure. The platform also supports upcoming BlueField-4 DPU technology to further enhance security and performance for AI inference workloads from core to edge.

Initially available in 20 global locations, Akamai plans an accelerated global rollout to extend its reach and performance footprint.

Strategic Impact

The collaboration between Akamai and NVIDIA represents a pivotal shift toward distributed, generative edge computing, setting the foundation for real-time AI everywhere, across digital experiences, industrial systems, and autonomous applications.

Read More:

DEP’s Basant Sharma: AI and Digital Twins will define India’s next wave of manufacturing

How enterprise cloud is transforming in India with AI-native innovation?

US tariff shock reshapes India’s IT strategy: how disruption is driving resilience

Inside Veeam’s ProPartner strategy: What’s next for data protection