SlideShare a Scribd company logo
How to Right-Size and Future-
Proof a Container-First Edge AI
Infrastructure
Carl Moberg
CTO at Avassa
Zoie Rittling
Business Development Manager at OnLogic
Edge AI: There’s more to it than the model and the
application
Edge AI starts with a model
and an application…
© 2025 Avassa / OnLogic 2
…but operating AI at the edge
in resource-constrained
environments also requires
scalable, purpose-built
infrastructure.
In this presentation we will…
• Learn what to consider when:
• Selecting edge AI devices
• Managing the lifecycle of edge AI applications
• Lay out the components of a best-of-breed approach to an edge AI stack
© 2025 Avassa / OnLogic 3
Introducing Avassa
© 2025 Avassa / OnLogic 4
Introducing OnLogic
Millions of Configurations
Systems tailored for your exact needs
Collaborative Sales Approach
No middleman when it comes to solving your challenges
Engineered for the Edge
Rugged and reliable performance where it matters most
Prototype to Production
Our engineers can design, deploy, and scale any project
Built for scale
Expansive global production capacity to meet growing demand
© 2025 Avassa / OnLogic 5
Traditional view of the edge
© 2025 Avassa / OnLogic 6
What do I need to consider when selecting edge devices?
© 2025 Avassa / OnLogic 7
… The edge is a complex place with different and diverse
challenges.
Temperature Dust Constrained
space
Vibration
© 2025 Avassa / OnLogic
Edge hardware considerations
8
8
What do I need to consider when managing edge AI applications?
9
© 2025 Avassa / OnLogic
MLOps meets lifecycle management
10
MLOps
Lifecycle
Management
File
ready to
deploy
© 2025 Avassa / OnLogic
Purpose-driven model lifecycle management
© 2025 Avassa / OnLogic 11
Model version 1 Model Container Layer
Container Layers
Model Serving Container Layer
Time
Model serving
system
Deployed
container v 1.0
Purpose-driven model lifecycle management
© 2025 Avassa / OnLogic 12
Model version 1 Model version 2
Time
The very same model serving system version
Deployed
container v 1.1
Model Container Layer
Container Layers
Model Serving Container Layer
Purpose-driven model lifecycle management
© 2025 Avassa / OnLogic 13
Model version 1 Model version 2 Model version 3
Time
The very same model serving system version
Deployed
container v 1.2
Model Container Layer
Container Layers
Model Serving Container Layer
Targeted deployments of containers, only where they are
needed
14
Control Tower
Targeted deployments
• Declarative requirements in
your application
• Define what and where
• Automatic placement of
application at the edge
Discovery and rule-based labels
Automatic discovery
• Leaf device discovery using
Linux kernel features
• Local rule-based label
management
• Automatic identification and
mounting of local devices
• Local placement based on
GPU availability
for application placement
© 2025 Avassa / OnLogic
Lifecycle managing AI models at the edge
© 2025 Avassa / OnLogic 15
Edge
Application
developer
Edge
IT/Platform
engineer
Re-utilize existing investment and
integrate with current systems
Allow for offline scenarios by making sure your
key application services are kept local
Key considerations:
Hardware and GPU requirements
drive application placements
The model changes faster
than the application
Remote
management
at scale
Control
Tower
Why best of breed?
© 2025 Avassa / OnLogic 16
Avoid silos and redundant stacks
© 2025 Avassa / OnLogic 17
The cloud The edge
Operational
dashboard
Application
Siloed hardware
Operational
dashboard
Operational
dashboard
Application
Siloed hardware
Application
Siloed hardware
Traditional silos with application-by-
application infrastructure solutions
Avoid silos and redundant stacks
© 2025 Avassa / OnLogic 18
The cloud The edge
OnLogic Device
Operational
dashboard Application
Application
Application
Application
Application
A modern unified platform with streamlined
infrastructure and single-pane-of-glass overview
The cloud The edge
Operational
dashboard
Application
Siloed hardware
Operational
dashboard
Operational
dashboard
Application
Siloed hardware
Application
Siloed hardware
Traditional silos with application-by-
application infrastructure solutions
Hardware that withstands its environment
© 2025 Avassa / OnLogic
● Fanless or active cooling
● x86 and ARM architecture
● Industrial operating temp.
(0-50°C)
Rugged Computers
Industrial Computers
● Resistant to shock & vibration
● Wide input (12-48VDC)
● Wide operating temp. (-40-
70°C)
Panel PCs / HMIs
● 8.4” to 24” screen sizes
● Resistive or capacitive
touch
● Up to IP69K ingress
protection
Edge Servers
● 1U to 4U sizes
● Intel and AMD options
● Highly customizable
19
A modern, right-sized infrastructure stack for edge AI
© 2025 Avassa / OnLogic 20
Edge Platform
Industrial PCs & HMIs
Sensors, Actuators, PLCs
App App
Data & Cloud Integration
AI
…
MLOps integrations to continuously deploy and monitor
AI workloads through APIs
AI workloads comprise several parts (server, code,
model, configuration) with separate lifecycle needs
CPUs with integrated GPUs and NPUs for efficiency,
dedicated accelerators when needed.
Control logic going virtual – towards distributed,
software-defined control architectures.
A modern, right-sized infrastructure stack for edge AI
© 2025 Avassa / OnLogic 21
Edge Platform
Industrial PCs & HMIs
Sensors, Actuators, PLCs
App App
Data & Cloud Integration
AI
…
A unified stack, allowing
multiple workloads to share
common infrastructure
Conclusions
• Edge AI success demands rugged hardware,
scalable orchestration, and seamless cloud
integration — not just smarter models.
• A best-of-breed stack right-sized infrastructure
prevents silos and manual overhead, unlocking a
unified, agile, and scalable edge environment
ready for the challenges of tomorrow.
• Pairing industrial-grade devices with smart
application management builds Edge AI systems
that adapt and thrive over time.
© 2025 Avassa / OnLogic 22
Making the edge lovable for your
development and application operations
team
Optimizing Edge AI: Combining MLOps
and Edge Orchestration for Success
Solution description: Avassa for Edge AI
Solution description: OnLogic for Edge AI
2025 Embedded Vision Summit
Come see us at booth 521!
Carl Moberg
calle@avassa.io
Zoie Rittling
zoie.rittling@onlogic.com
© 2025 Avassa / OnLogic 23
Resources

More Related Content

Similar to “How to Right-size and Future-proof a Container-first Edge AI Infrastructure,” a Presentation from Avassa and OnLogic (20)

PPTX
IoTSummit: Create iot devices connected or on the edge using ai and ml
Marco Dal Pino
 
PDF
Edge computing and its role in architecting IoT
Kiran Kumar Pattanaik
 
PDF
Automated Deployment and Management of Edge Clouds
Jay Bryant
 
PDF
Deploy and Manage Your Industrial IoT Edge Solutions In Weeks With EdgeOps
Tredence Inc
 
PPTX
Azure iot edge and AI enabling the intelligent edge
Marco Dal Pino
 
PPTX
Maturing IoT solutions with Microsoft Azure (Sam Vanhoutte & Glenn Colpaert a...
Codit
 
PDF
Exploring the Trend Toward the Edge | Eclipse IoT Day Santa Clara 2019
Eclipse IoT
 
PPTX
Internet of things at the Edge with Azure IoT Edge by sonujose
Sonu Jose
 
PPTX
External SEDC cussadasdasdsadtomer brief.pptx
dusanheliant
 
PPTX
Exploring IoT Edge
Codit
 
PDF
Converged IoT Systems: Bringing the Data Center to the Edge of Everything
Dana Gardner
 
PPTX
Why integration is key in IoT solutions? (Sam Vanhoutte @Integrate2017)
Codit
 
PDF
Leveraging IoT as part of your digital transformation
John Archer
 
PDF
Foundational Elements for IoT (1)
Nicolas Delorme
 
PPTX
Digital transformation and AI @Edge
Institute of Contemporary Sciences
 
PPTX
Hybrid AI-Electronic Systems for Real-Time Edge Processing in IoT Networks.pptx
quilltechamazon
 
PDF
Introduction to Edge Computing using Google IoT
Volodymyr Rudyi
 
PDF
What is edge AI?
Antenna Manufacturer Coco
 
PPTX
Volwassen IoT-oplossingen met Microsoft Azure (Sam Vanhoutte at CONNECT17)
Codit
 
PDF
Architecting Iot Solutions On Azure Conquering Complexity For Scalable Device...
gendyhajra32
 
IoTSummit: Create iot devices connected or on the edge using ai and ml
Marco Dal Pino
 
Edge computing and its role in architecting IoT
Kiran Kumar Pattanaik
 
Automated Deployment and Management of Edge Clouds
Jay Bryant
 
Deploy and Manage Your Industrial IoT Edge Solutions In Weeks With EdgeOps
Tredence Inc
 
Azure iot edge and AI enabling the intelligent edge
Marco Dal Pino
 
Maturing IoT solutions with Microsoft Azure (Sam Vanhoutte & Glenn Colpaert a...
Codit
 
Exploring the Trend Toward the Edge | Eclipse IoT Day Santa Clara 2019
Eclipse IoT
 
Internet of things at the Edge with Azure IoT Edge by sonujose
Sonu Jose
 
External SEDC cussadasdasdsadtomer brief.pptx
dusanheliant
 
Exploring IoT Edge
Codit
 
Converged IoT Systems: Bringing the Data Center to the Edge of Everything
Dana Gardner
 
Why integration is key in IoT solutions? (Sam Vanhoutte @Integrate2017)
Codit
 
Leveraging IoT as part of your digital transformation
John Archer
 
Foundational Elements for IoT (1)
Nicolas Delorme
 
Digital transformation and AI @Edge
Institute of Contemporary Sciences
 
Hybrid AI-Electronic Systems for Real-Time Edge Processing in IoT Networks.pptx
quilltechamazon
 
Introduction to Edge Computing using Google IoT
Volodymyr Rudyi
 
What is edge AI?
Antenna Manufacturer Coco
 
Volwassen IoT-oplossingen met Microsoft Azure (Sam Vanhoutte at CONNECT17)
Codit
 
Architecting Iot Solutions On Azure Conquering Complexity For Scalable Device...
gendyhajra32
 

More from Edge AI and Vision Alliance (20)

PDF
“NPU IP Hardware Shaped Through Software and Use-case Analysis,” a Presentati...
Edge AI and Vision Alliance
 
PDF
“Voice Interfaces on a Budget: Building Real-time Speech Recognition on Low-c...
Edge AI and Vision Alliance
 
PDF
“Computer Vision at Sea: Automated Fish Tracking for Sustainable Fishing,” a ...
Edge AI and Vision Alliance
 
PDF
“Squinting Vision Pipelines: Detecting and Correcting Errors in Vision Models...
Edge AI and Vision Alliance
 
PDF
“ONNX and Python to C++: State-of-the-art Graph Compilation,” a Presentation ...
Edge AI and Vision Alliance
 
PDF
“Beyond the Demo: Turning Computer Vision Prototypes into Scalable, Cost-effe...
Edge AI and Vision Alliance
 
PDF
“Running Accelerated CNNs on Low-power Microcontrollers Using Arm Ethos-U55, ...
Edge AI and Vision Alliance
 
PDF
“Scaling i.MX Applications Processors’ Native Edge AI with Discrete AI Accele...
Edge AI and Vision Alliance
 
PDF
“A Re-imagination of Embedded Vision System Design,” a Presentation from Imag...
Edge AI and Vision Alliance
 
PDF
“MPU+: A Transformative Solution for Next-Gen AI at the Edge,” a Presentation...
Edge AI and Vision Alliance
 
PDF
“Evolving Inference Processor Software Stacks to Support LLMs,” a Presentatio...
Edge AI and Vision Alliance
 
PDF
“Efficiently Registering Depth and RGB Images,” a Presentation from eInfochips
Edge AI and Vision Alliance
 
PDF
“Image Tokenization for Distributed Neural Cascades,” a Presentation from Goo...
Edge AI and Vision Alliance
 
PDF
“Key Requirements to Successfully Implement Generative AI in Edge Devices—Opt...
Edge AI and Vision Alliance
 
PDF
“Bridging the Gap: Streamlining the Process of Deploying AI onto Processors,”...
Edge AI and Vision Alliance
 
PDF
“From Enterprise to Makers: Driving Vision AI Innovation at the Extreme Edge,...
Edge AI and Vision Alliance
 
PDF
“Addressing Evolving AI Model Challenges Through Memory and Storage,” a Prese...
Edge AI and Vision Alliance
 
PDF
“Why It’s Critical to Have an Integrated Development Methodology for Edge AI,...
Edge AI and Vision Alliance
 
PDF
“Solving Tomorrow’s AI Problems Today with Cadence’s Newest Processor,” a Pre...
Edge AI and Vision Alliance
 
PDF
“State-space Models vs. Transformers for Ultra-low-power Edge AI,” a Presenta...
Edge AI and Vision Alliance
 
“NPU IP Hardware Shaped Through Software and Use-case Analysis,” a Presentati...
Edge AI and Vision Alliance
 
“Voice Interfaces on a Budget: Building Real-time Speech Recognition on Low-c...
Edge AI and Vision Alliance
 
“Computer Vision at Sea: Automated Fish Tracking for Sustainable Fishing,” a ...
Edge AI and Vision Alliance
 
“Squinting Vision Pipelines: Detecting and Correcting Errors in Vision Models...
Edge AI and Vision Alliance
 
“ONNX and Python to C++: State-of-the-art Graph Compilation,” a Presentation ...
Edge AI and Vision Alliance
 
“Beyond the Demo: Turning Computer Vision Prototypes into Scalable, Cost-effe...
Edge AI and Vision Alliance
 
“Running Accelerated CNNs on Low-power Microcontrollers Using Arm Ethos-U55, ...
Edge AI and Vision Alliance
 
“Scaling i.MX Applications Processors’ Native Edge AI with Discrete AI Accele...
Edge AI and Vision Alliance
 
“A Re-imagination of Embedded Vision System Design,” a Presentation from Imag...
Edge AI and Vision Alliance
 
“MPU+: A Transformative Solution for Next-Gen AI at the Edge,” a Presentation...
Edge AI and Vision Alliance
 
“Evolving Inference Processor Software Stacks to Support LLMs,” a Presentatio...
Edge AI and Vision Alliance
 
“Efficiently Registering Depth and RGB Images,” a Presentation from eInfochips
Edge AI and Vision Alliance
 
“Image Tokenization for Distributed Neural Cascades,” a Presentation from Goo...
Edge AI and Vision Alliance
 
“Key Requirements to Successfully Implement Generative AI in Edge Devices—Opt...
Edge AI and Vision Alliance
 
“Bridging the Gap: Streamlining the Process of Deploying AI onto Processors,”...
Edge AI and Vision Alliance
 
“From Enterprise to Makers: Driving Vision AI Innovation at the Extreme Edge,...
Edge AI and Vision Alliance
 
“Addressing Evolving AI Model Challenges Through Memory and Storage,” a Prese...
Edge AI and Vision Alliance
 
“Why It’s Critical to Have an Integrated Development Methodology for Edge AI,...
Edge AI and Vision Alliance
 
“Solving Tomorrow’s AI Problems Today with Cadence’s Newest Processor,” a Pre...
Edge AI and Vision Alliance
 
“State-space Models vs. Transformers for Ultra-low-power Edge AI,” a Presenta...
Edge AI and Vision Alliance
 
Ad

Recently uploaded (20)

PPTX
Digital Circuits, important subject in CS
contactparinay1
 
PDF
UiPath DevConnect 2025: Agentic Automation Community User Group Meeting
DianaGray10
 
PDF
Reverse Engineering of Security Products: Developing an Advanced Microsoft De...
nwbxhhcyjv
 
PDF
The Rise of AI and IoT in Mobile App Tech.pdf
IMG Global Infotech
 
PDF
Staying Human in a Machine- Accelerated World
Catalin Jora
 
DOCX
Cryptography Quiz: test your knowledge of this important security concept.
Rajni Bhardwaj Grover
 
PPTX
MuleSoft MCP Support (Model Context Protocol) and Use Case Demo
shyamraj55
 
PDF
AI Agents in the Cloud: The Rise of Agentic Cloud Architecture
Lilly Gracia
 
PPTX
Agentforce World Tour Toronto '25 - Supercharge MuleSoft Development with Mod...
Alexandra N. Martinez
 
PDF
CIFDAQ Market Wrap for the week of 4th July 2025
CIFDAQ
 
PDF
Go Concurrency Real-World Patterns, Pitfalls, and Playground Battles.pdf
Emily Achieng
 
PDF
Transforming Utility Networks: Large-scale Data Migrations with FME
Safe Software
 
PDF
Peak of Data & AI Encore AI-Enhanced Workflows for the Real World
Safe Software
 
PPT
Ericsson LTE presentation SEMINAR 2010.ppt
npat3
 
PDF
Transcript: Book industry state of the nation 2025 - Tech Forum 2025
BookNet Canada
 
PPTX
COMPARISON OF RASTER ANALYSIS TOOLS OF QGIS AND ARCGIS
Sharanya Sarkar
 
PDF
Bitcoin for Millennials podcast with Bram, Power Laws of Bitcoin
Stephen Perrenod
 
PPTX
Mastering ODC + Okta Configuration - Chennai OSUG
HathiMaryA
 
PPTX
Q2 FY26 Tableau User Group Leader Quarterly Call
lward7
 
PDF
What’s my job again? Slides from Mark Simos talk at 2025 Tampa BSides
Mark Simos
 
Digital Circuits, important subject in CS
contactparinay1
 
UiPath DevConnect 2025: Agentic Automation Community User Group Meeting
DianaGray10
 
Reverse Engineering of Security Products: Developing an Advanced Microsoft De...
nwbxhhcyjv
 
The Rise of AI and IoT in Mobile App Tech.pdf
IMG Global Infotech
 
Staying Human in a Machine- Accelerated World
Catalin Jora
 
Cryptography Quiz: test your knowledge of this important security concept.
Rajni Bhardwaj Grover
 
MuleSoft MCP Support (Model Context Protocol) and Use Case Demo
shyamraj55
 
AI Agents in the Cloud: The Rise of Agentic Cloud Architecture
Lilly Gracia
 
Agentforce World Tour Toronto '25 - Supercharge MuleSoft Development with Mod...
Alexandra N. Martinez
 
CIFDAQ Market Wrap for the week of 4th July 2025
CIFDAQ
 
Go Concurrency Real-World Patterns, Pitfalls, and Playground Battles.pdf
Emily Achieng
 
Transforming Utility Networks: Large-scale Data Migrations with FME
Safe Software
 
Peak of Data & AI Encore AI-Enhanced Workflows for the Real World
Safe Software
 
Ericsson LTE presentation SEMINAR 2010.ppt
npat3
 
Transcript: Book industry state of the nation 2025 - Tech Forum 2025
BookNet Canada
 
COMPARISON OF RASTER ANALYSIS TOOLS OF QGIS AND ARCGIS
Sharanya Sarkar
 
Bitcoin for Millennials podcast with Bram, Power Laws of Bitcoin
Stephen Perrenod
 
Mastering ODC + Okta Configuration - Chennai OSUG
HathiMaryA
 
Q2 FY26 Tableau User Group Leader Quarterly Call
lward7
 
What’s my job again? Slides from Mark Simos talk at 2025 Tampa BSides
Mark Simos
 
Ad

“How to Right-size and Future-proof a Container-first Edge AI Infrastructure,” a Presentation from Avassa and OnLogic

  • 1. How to Right-Size and Future- Proof a Container-First Edge AI Infrastructure Carl Moberg CTO at Avassa Zoie Rittling Business Development Manager at OnLogic
  • 2. Edge AI: There’s more to it than the model and the application Edge AI starts with a model and an application… © 2025 Avassa / OnLogic 2 …but operating AI at the edge in resource-constrained environments also requires scalable, purpose-built infrastructure.
  • 3. In this presentation we will… • Learn what to consider when: • Selecting edge AI devices • Managing the lifecycle of edge AI applications • Lay out the components of a best-of-breed approach to an edge AI stack © 2025 Avassa / OnLogic 3
  • 4. Introducing Avassa © 2025 Avassa / OnLogic 4
  • 5. Introducing OnLogic Millions of Configurations Systems tailored for your exact needs Collaborative Sales Approach No middleman when it comes to solving your challenges Engineered for the Edge Rugged and reliable performance where it matters most Prototype to Production Our engineers can design, deploy, and scale any project Built for scale Expansive global production capacity to meet growing demand © 2025 Avassa / OnLogic 5
  • 6. Traditional view of the edge © 2025 Avassa / OnLogic 6
  • 7. What do I need to consider when selecting edge devices? © 2025 Avassa / OnLogic 7
  • 8. … The edge is a complex place with different and diverse challenges. Temperature Dust Constrained space Vibration © 2025 Avassa / OnLogic Edge hardware considerations 8 8
  • 9. What do I need to consider when managing edge AI applications? 9 © 2025 Avassa / OnLogic
  • 10. MLOps meets lifecycle management 10 MLOps Lifecycle Management File ready to deploy © 2025 Avassa / OnLogic
  • 11. Purpose-driven model lifecycle management © 2025 Avassa / OnLogic 11 Model version 1 Model Container Layer Container Layers Model Serving Container Layer Time Model serving system Deployed container v 1.0
  • 12. Purpose-driven model lifecycle management © 2025 Avassa / OnLogic 12 Model version 1 Model version 2 Time The very same model serving system version Deployed container v 1.1 Model Container Layer Container Layers Model Serving Container Layer
  • 13. Purpose-driven model lifecycle management © 2025 Avassa / OnLogic 13 Model version 1 Model version 2 Model version 3 Time The very same model serving system version Deployed container v 1.2 Model Container Layer Container Layers Model Serving Container Layer
  • 14. Targeted deployments of containers, only where they are needed 14 Control Tower Targeted deployments • Declarative requirements in your application • Define what and where • Automatic placement of application at the edge Discovery and rule-based labels Automatic discovery • Leaf device discovery using Linux kernel features • Local rule-based label management • Automatic identification and mounting of local devices • Local placement based on GPU availability for application placement © 2025 Avassa / OnLogic
  • 15. Lifecycle managing AI models at the edge © 2025 Avassa / OnLogic 15 Edge Application developer Edge IT/Platform engineer Re-utilize existing investment and integrate with current systems Allow for offline scenarios by making sure your key application services are kept local Key considerations: Hardware and GPU requirements drive application placements The model changes faster than the application Remote management at scale Control Tower
  • 16. Why best of breed? © 2025 Avassa / OnLogic 16
  • 17. Avoid silos and redundant stacks © 2025 Avassa / OnLogic 17 The cloud The edge Operational dashboard Application Siloed hardware Operational dashboard Operational dashboard Application Siloed hardware Application Siloed hardware Traditional silos with application-by- application infrastructure solutions
  • 18. Avoid silos and redundant stacks © 2025 Avassa / OnLogic 18 The cloud The edge OnLogic Device Operational dashboard Application Application Application Application Application A modern unified platform with streamlined infrastructure and single-pane-of-glass overview The cloud The edge Operational dashboard Application Siloed hardware Operational dashboard Operational dashboard Application Siloed hardware Application Siloed hardware Traditional silos with application-by- application infrastructure solutions
  • 19. Hardware that withstands its environment © 2025 Avassa / OnLogic ● Fanless or active cooling ● x86 and ARM architecture ● Industrial operating temp. (0-50°C) Rugged Computers Industrial Computers ● Resistant to shock & vibration ● Wide input (12-48VDC) ● Wide operating temp. (-40- 70°C) Panel PCs / HMIs ● 8.4” to 24” screen sizes ● Resistive or capacitive touch ● Up to IP69K ingress protection Edge Servers ● 1U to 4U sizes ● Intel and AMD options ● Highly customizable 19
  • 20. A modern, right-sized infrastructure stack for edge AI © 2025 Avassa / OnLogic 20 Edge Platform Industrial PCs & HMIs Sensors, Actuators, PLCs App App Data & Cloud Integration AI … MLOps integrations to continuously deploy and monitor AI workloads through APIs AI workloads comprise several parts (server, code, model, configuration) with separate lifecycle needs CPUs with integrated GPUs and NPUs for efficiency, dedicated accelerators when needed. Control logic going virtual – towards distributed, software-defined control architectures.
  • 21. A modern, right-sized infrastructure stack for edge AI © 2025 Avassa / OnLogic 21 Edge Platform Industrial PCs & HMIs Sensors, Actuators, PLCs App App Data & Cloud Integration AI … A unified stack, allowing multiple workloads to share common infrastructure
  • 22. Conclusions • Edge AI success demands rugged hardware, scalable orchestration, and seamless cloud integration — not just smarter models. • A best-of-breed stack right-sized infrastructure prevents silos and manual overhead, unlocking a unified, agile, and scalable edge environment ready for the challenges of tomorrow. • Pairing industrial-grade devices with smart application management builds Edge AI systems that adapt and thrive over time. © 2025 Avassa / OnLogic 22
  • 23. Making the edge lovable for your development and application operations team Optimizing Edge AI: Combining MLOps and Edge Orchestration for Success Solution description: Avassa for Edge AI Solution description: OnLogic for Edge AI 2025 Embedded Vision Summit Come see us at booth 521! Carl Moberg [email protected] Zoie Rittling [email protected] © 2025 Avassa / OnLogic 23 Resources