[May, 2025] Mobilint Unveils AWS Collaboration and New Edge AI Accelerator at Embedded Vision Summit 2025
- Mar 18
- 2 min read
Santa Clara, CA | May 21, 2025 — Mobilint, a fast-growing AI semiconductor startup and portfolio company of the Korea AI & System IC Innovation Center (K-ASIC), announced a strategic collaboration with Amazon Web Services (AWS) during its participation in Embedded Vision Summit 2025, held at the Santa Clara Convention Center.
Building on initial discussions at CES 2025, Mobilint and AWS are advancing the integration of Mobilint’s high-performance NPU (Neural Processing Unit) with AWS IoT Greengrass, enabling scalable edge AI deployment. The collaboration includes joint go-to-market initiatives and customer engagement strategies aimed at accelerating adoption of on-device AI across a wide range of edge applications.
At the event, Mobilint unveiled its collaboration roadmap and showcased real-world use cases powered by its newly launched MLA100 MXM module, drawing strong interest from developers, industry leaders, and potential partners.
The integration enables AWS customers to leverage Mobilint’s NPU for:
Real-time AI inference at the edge
Local processing of sensitive data without cloud dependency
Latency-optimized AI workloads for mission-critical applications
In addition, Mobilint plans to integrate its NPU SDK with Amazon SageMaker, providing a seamless end-to-end AI workflow—from model training to edge deployment—enhancing developer productivity and system efficiency.
“This collaboration represents a strategic step toward delivering unified, NPU-powered edge AI solutions to the global market,” said Dongjoo Shin, CEO of Mobilint. “We are accelerating co-marketing and customer acquisition efforts with AWS following strong industry interest at EVS.”
Expanding Global Presence in AI Semiconductors
Mobilint’s presence at Embedded Vision Summit 2025 builds on its recent global engagements at CES (Las Vegas) and MWC (Barcelona), where the company demonstrated its ability to run large language models (LLMs) directly on-device without reliance on cloud infrastructure.
At the core of its product portfolio is REGULUS, a proprietary NPU architecture designed to deliver 5–10x lower power consumption and cost compared to traditional GPU-based solutions. This enables efficient deployment across key applications such as robotics, drones, consumer electronics, and industrial AI systems.
Product Highlight: MLA100 MXM Edge AI Accelerator
In April 2025, Mobilint introduced the MLA100 MXM, a compact edge AI accelerator built on its flagship ERIS chip. Key specifications include:
Up to 80 TOPS performance at 25W power consumption
Eight-core architecture for parallel AI model execution
Support for LLMs, VLMs, and transformer-based models
Ultra-compact 82mm × 70mm form factor and 110g weight, optimized for edge servers, robotics, and industrial systems
Driving the Next Wave of Edge AI Innovation
Through its collaboration with AWS and continued product innovation, Mobilint is positioning itself as a key player in the global edge AI semiconductor market. The company’s focus on high-performance, energy-efficient NPU solutions aligns with the growing demand for decentralized AI processing and real-time intelligence at the edge.
K-ASIC will continue to support Mobilint and its portfolio companies in expanding global partnerships, accelerating commercialization, and strengthening Korea’s presence in the next generation of AI semiconductor technologies.