The way to Edge AI

Abstract

As telecommunications evolves toward 6G, Radio Access Networks (RAN) will fundamentally transform application architecture beyond today’s approach of endpoints calling LLMs on remote data centers. This presentation examines three critical software development challenges for the next decade:

• Real-time AI at the Edge: Moving from cloud-dependent inference to distributed processing meeting RAN’s strict latency requirements.
• Multi-tenant Resource Optimization: Transitioning to shared platforms where AI workloads coexist while maintaining service-level agreements.
• Federated Learning and Privacy: Shifting from centralized training to federated approaches preserving privacy across distributed networks.

The goal is sharing a roadmap for AI-native infrastructure where intelligence lives at the network edge.

Bio

Alisson Sol is a hands-on executive specializing in Edge AI with extensive experience in software development. He has successfully built and managed teams that delivered applications, services, and frameworks across diverse domains. His technical expertise spans Computer Vision, Machine Learning, Big Data, Cybersecurity, and Distributed Systems.

Since December/2023, he works as VP of Software Engineering for Capital One in New York, NY. Previously, he worked as an Engineering Manager for the Google Security Fundamentals team in New York, NY, from May/2022 to December/2023. He worked twice for Microsoft Corporation, from 2000 to 2022, in several teams in the Seattle, WA area and for Microsoft Research in Cambridge, UK. From 2017 to 2019, he was a Senior Development Manager for Amazon, working in the AWS WorkSpaces and the direct fulfillment (dropship) teams. He was previously a co-founder of 3 software companies, published several technical papers, and has several patent applications and granted patents.

He has a B.Sc. in Physics and an M.Sc. in Computer Science from the Federal University of Minas Gerais in Brazil and General Management training at the University of Cambridge-UK. When not coding, he likes to run half-marathons, play soccer, disassemble hardware, put it back to work, and reuse the spare parts elsewhere!