OCTOBER 15, 2026
11:00 – 16:00
Hypersolid, Alkmaar studio
Keesomstraat 10 E, 1821 BS
Alkmaar, Netherlands
STREAMING ARCHITECTURE: FROM SILICON TO SCREEN
Encoding efficiency at scale: from VPU hardware to orchestration to the viewer’s screen.
Built for the people who design, build and operate streaming platforms: Streaming & video platform engineers | Infrastructure & encoding architects | Head end & playout teams | Broadcasters, telcos & OTT services | Systems integrators & platform builders
ABOUT THE EVENT
Following the Stockholm edition, NETINT, Scalstrm and Hypersolid come together in the Netherlands to show how a modern streaming platform is built from end to end: efficient VPU based encoding, intelligent orchestration, and the experience layer that reaches the viewer.
The day follows one arc: why VPUs matter, what makes them deployable at scale, and a live deployment that proves the full stack in production. Expect practical sessions, a real world deployment teardown, and open technical discussion. The room is kept small, at around 60 attendees.
AGENDA
Registration, with coffee and a light breakfast, and time to settle in and network before we begin.
The systems view across the full delivery chain, from ingest and encoding through packaging, DRM, CDN and multi device playback. Where the hard integration problems live: latency budgets, player and device fragmentation, ABR behaviour and operational resilience, and why efficiency at the encode tier changes the economics of everything downstream.
The real cost drivers in an encoding tier: transcode density per rack unit, watts per concurrent stream, and dollar per channel across H.264, HEVC and AV1. A comparison of general purpose CPU and GPU transcoding with dedicated ASIC based VPUs, and where software only pipelines hit throughput, power and thermal ceilings as channel counts scale.
The encode path on a VPU, end to end: decode, scaling and filtering, then parallel multi bitrate encode across H.264, HEVC, AV1 and VP9 at 8 and 10 bit, up to 8K. FFmpeg integration, per stream tuning, GOP and rate control behaviour, concurrency limits, and the PCIe and IO considerations that decide real world channel counts per server.
The software stack that turns raw hardware into a production platform: live transcoding, packaging to HLS and DASH with CMAF, encryption and DRM, origin and delivery, orchestrated as one system. How work is scheduled across a VPU pool to keep utilisation high while holding latency and quality targets and cutting infrastructure and energy cost.
Lunch, followed by a guided tour of the Hypersolid studio in two waves. The building is an experience in itself: the media testing lab, innovation lab, esports training room, recording studios, the old mobile phone wall, LEGO displays, the resident honeybees, and a racing simulator built around Max Verstappen’s own setup.
Under the hood of the orchestration layer: job queueing and scheduling, workload placement across VPU resources, autoscaling under uneven load, failover and redundancy for channels that cannot go dark, and the observability to run it, including per stream telemetry and VPU health. Covers both modern OTT and legacy transport such as MPTS and SPTS.
A full architecture teardown of a real deployment running many live channels on VPUs, orchestrated by Scalstrm, behind a viewer platform built by Hypersolid. The end to end path, the sizing and density numbers achieved, the failure modes encountered and engineered around, and the concrete lessons from production.
A live walk through of bringing a VPU into an existing FFmpeg based pipeline: device selection and passthrough, the command and flag changes, running concurrent encodes, and reading live throughput and card telemetry. Plus the common pitfalls: IO bottlenecks, scaling assumptions and how to validate output.
Coffee, tea and networking.
Where the stack is heading at a technical level: codec support, density and performance gains on the hardware side, and platform, orchestration and delivery capabilities on the software side. What teams can design and build toward next.
An open, engineer to engineer debate across the full stack, silicon to screen. Where the real gains live: dedicated hardware, the orchestration and transcoding layer, or end to end architecture choices, plus codecs, density, and cloud versus hybrid trade offs. Bring the questions the day raised.
Speakers from NETINT, Scalstrm, and Hypersolid
Engineers and architects working on real-world streaming systems
Business Development & Sales Director
With over 20 years of experience in Digital TV, Broadcasting, Networking, and Advertising, Dominique Vosters bridges the gap between complex engineering and business impact. As the Business Development & Sales Director at Scalstrm, he drives sustainable and efficient media delivery, optimizing streaming performance while reducing costs and energy consumption. His expertise spans solution design, technical sales, and large-scale deployments.
Chief Growth Officer
Michael Plein turns technology into growth. As Chief Growth Officer at Hypersolid (formerly Triple), he leads expansion across the Media, Sports and Entertainment industry in the EU and the development of new AI enabled propositions. With two decades building one of the Netherlands’ most innovative digital agencies, his work spans content solutions, large scale operations, and partnerships from Heineken and VodafoneZiggo to the digital branding of F1 world champion Max Verstappen.
CRO
With a career spanning video, broadcast and networking leadership at Ericsson, Scientific Atlanta and Cisco, Randal Horne connects deep industry experience to commercial growth. As Chief Revenue Officer at NETINT, he leads global sales and go to market for the company’s VPU technology, working with the streaming platforms, operators and broadcasters adopting dedicated video hardware at scale. His focus is turning the cost, power and density advantages of VPUs into real world deployments.
Director of Market Development, EMEA
Leonardo Nieto represents NETINT across EMEA, working closely with streaming platforms, telecom operators, and infrastructure providers scaling video in power- and cost-constrained environments. With experience spanning applied transcoding, live streaming, and high-growth technology ventures, he focuses on the practical realities of deployment: density per rack, watts per stream, codec transitions, and cloud versus edge trade-offs.
Business Development Manager, EMEA
Niklas Ruottu leads go to market for NETINT across EMEA, focused on new customer acquisition and strategic partnerships as the VPU ecosystem expands in the region. He brings more than 10 years in cloud infrastructure, media and telecommunications, including five years at Oracle building cloud business with streaming, gaming and AI software vendors. Certified across all four major cloud platforms, he helps video teams weigh the cost and performance trade offs of running at scale in the cloud, on premises or hybrid.
Field Application Engineer
Arek Chojak is a Field Application Engineer at NETINT, focused on the real world deployment of VPU based encoding and streaming workflows. He brings deep hands on experience from across live streaming and broadcast, including nearly six years at AWS Elemental and engineering roles at DAZN, Perform Group and Techex, spanning live encoding and transcoding, OTT delivery, IP contribution and CDN workflows. His strengths are Linux, broadcast systems, and solving complex performance and scaling problems in production.
Field Application Engineer
Craig Butlin is a Field Application Engineer at NETINT Technologies, focused on real-world deployment of video encoding and streaming workflows. With a background spanning AWS Elemental, Ericsson, Amagi, and Techex, he brings hands-on experience across cloud, broadcast, and large-scale media systems. Craig specializes in practical integration, debugging, and performance optimization, helping teams understand how encoding infrastructure behaves in production and how to scale efficiently.
VENUE & GETTING THERE
Hypersolid, Alkmaar studio
Keesomstraat 10 E, 1821 BS Alkmaar, Netherlands
Doors open 10:30 · Programme 11:00 to 16:00
How to get there
- By train: about 38 minutes direct from Amsterdam Centraal. From Alkmaar station a bus runs every 10 minutes to the P and R next to the office (about a 5 minute ride).
- From Schiphol Airport: about 45 to 55 minutes by direct train to Alkmaar.
- By car: free parking directly outside the office. About 45 to 60 minutes from Amsterdam.
Worth watching, whether or not you join us
Sessions from our last edition
A few sessions from the series, shared for anyone working on streaming infrastructure. Practical talks on how encoding actually runs, where real throughput is won, and what changes when VPUs enter the pipeline. Useful whether or not you can make it to Alkmaar.
How Video Encoding Actually Runs: CPU vs Dedicated Hardware
Craig Butlin explains how video encoding works under the hood, from input and demuxing to decoding, preprocessing, scaling, and final encode. He compares CPU-based encoding with dedicated video hardware, showing why CPUs can struggle with sustained, high-throughput workloads and why VPUs offer more predictable performance, higher density, and better power efficiency at scale.
Unlocking True Throughput with NETINT VPUs in Live Streaming Workflows
Dominique Vosters explains how SCALSTRM uses NETINT VPUs inside a broader live streaming workflow that goes beyond basic transcoding. The session covers how VPU acceleration fits with CPU-side processing, frame repair, synchronization, packaging, audio handling, redundancy, and API-based management for carrier-grade live video delivery.
Integrating Hardware Encoding into an Existing FFmpeg Pipeline
Craig Butlin walks through a practical FFmpeg demo comparing software encoding with NETINT hardware encoding. He shows what actually changes in the pipeline, including decoder and encoder selection, hardware frames, filtering, scaling, and encode parameters, while demonstrating the performance difference between CPU-based and VPU-based transcoding.
VPU Product Brochures
