Real-time Analytics
FanDuel TV and Verizon needed a portable production architecture that could move high-volume live sports feeds with lower latency and stronger security than cloud backhaul while still supporting AI-assisted camera selection and on-site editorial control.
Reported impact
The pilot cut latency by more than 50 percent versus traditional cloud workflows, gave FanDuel immediate editorial control near the source, reduced hardware from multiple racks to one portable unit, and created a scalable path for AI-assisted production across more than 130 racetracks.
Verizon built its Private 5G Network with Enterprise AI for FanDuel TV as an on-site live-media stack that combines wireless connectivity, edge compute, and AI inference in one portable unit. Camera feeds are ingested over Verizon's licensed-spectrum private 5G network and processed at the edge with NVIDIA Holoscan for Media running on bare-metal infrastructure with NVIDIA L40S GPUs. NVIDIA AI Enterprise and NIM microservices support the AI runtime, which can apply object detection, feed prioritization, captioning, and other media workflows without sending traffic back to a remote cloud. The platform is SMPTE ST 2110 compliant and includes timing, control, and container orchestration so broadcasters can train and deploy custom LLM and VLM workflows on site while keeping sensitive live-production data local.
Live camera feeds are transmitted over Verizon's private 5G network into an edge compute module, where Holoscan for Media and NIM-backed services run on L40S GPUs. The AI layer analyzes video in real time to prioritize feeds, identify key race moments, and return low-latency outputs to producers so editorial control stays on site rather than in a distant cloud.
Built on NVIDIA Holoscan for Media, it enables real-time AI inference for video and audio and supports multi-vendor workflows via container orchestration.
FanDuel's pilot using Verizon's Private 5G Network with Enterprise AI running on NVIDIA AI Enterprise and Holoscan for Media achieved over 50% lower latency and enabled immediate editorial control near the source for live race production.
It runs on bare-metal infrastructure leveraging NVIDIA L40S GPUs for high-performance compute, networking, and storage.
This pilot shows how Private 5G and edge AI can transform high-volume live sports production.
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
NVIDIA Sample Aug 25, 2026 Neuron Systems Neuron Systems needed an always-on AI sports newsroom that could analyze every play, sustain multi-agent reasoning during long live broadcasts, and generate multilingual commentary without the latency, rate limits, and… 1 million audited AI traces NVIDIA CUDA · NVIDIA H100 GPUs 
Lenovo Sample Oct 13, 2026 Formula E Formula E wanted fan experiences that feel immediate, immersive, personalized, and participatory, but its broadcast and event experience was limited by inconsistent onboard video quality, information spread across… Developed in under 30 days. AI Fan Experience Guide · AI Video Optimization · AR broadcast graphics NVIDIA Sample Oct 9, 2026 California Department of Transportation (Caltrans) Caltrans needed to inspect and monitor roughly 1,200 active transportation projects more frequently and safely, but manual site visits were slow, inconsistent, and risky for staff working around traffic, bridges, and… Remote operations up to 100 miles Esri ArcGIS · NVIDIA CUDA · NVIDIA Jetson Orin 