Although Edge AI is moving quickly, deploying models in real industrial environments is still difficult. This webinar brings together OnLogic, Edge Impulse and Qualcomm to discuss how engineering teams can build more practical, production-ready edge AI systems for industrial and manufacturing applications.
The session will focus on rightsizing industrial edge AI, with a particular emphasis on Vision AI use cases such as inspection, monitoring, automation and quality control. Rather than defaulting to the largest model or most powerful hardware, engineers need to understand how to select the right model, compute platform and deployment architecture for each specific application.
You will learn how to balance model performance, compute, power, latency, cost, reliability and long-term deployment requirements. The discussion will explore where different model types fit within an industrial AI stack, from efficient vision models running at the edge, to SLMs, to more advanced agentic AI workflows.
We will also look at why smaller or more specialised models can often be the better engineering choice, especially when systems need to run reliably in production, integrate with existing infrastructure and avoid unnecessary deployment complexity.
What you’ll learn:
- What engineers need to consider when moving from prototype to deployment
- Why you might want to use less powerful AI models or compute hardware
- How to deploy Multi-model vision onto industrial hardware
- How to choose what model is active in multi-model systems
- How to balance compute, power, latency, accuracy, cost and reliability
- Where smaller models, SLMs and agentic AI workflows fit within an industrial AI stack
- How edge AI can support inspection, monitoring, quality control and automation
- How hardware and software choices affect long-term scalability and production readiness
Free