Athos Spins Out Of Mercedes With Chiplet Concept for AVs
By Sally Ward-Foxton, EETimes | October 17, 2025

After five years of technology incubation, Athos Silicon has officially spun out of Mercedes-Benz. The startup was founded in March 2025 based on a research project underway at Mercedes since 2020. Mercedes has made a strategic investment in Athos, including “substantial” IP, according to the company, and the OEM and its spinout will continue to collaborate on Athos’ mSoC reference design, Polaris.
As far back as 2020, the Athos team had been looking at how to address functional safety for autonomy since silicon on the market wasn’t sufficient, Athos CEO Charnjiv Bangar told EE Times.
“That led us on this journey of fundamentally looking at what is needed for highly reliable and safe compute,” he said. “We started with the problem of autonomy, and with problem statements from [Mercedes’] functional safety teams and application teams in Germany, and built the architecture from the ground up.”
To read the full article, click here
Related Chiplet
- DPIQ Tx PICs
- IMDD Tx PICs
- Near-Packaged Optics (NPO) Chiplet Solution
- High Performance Droplet
- Interconnect Chiplet
Related News
- Athos Silicon Selects DreamBig Semiconductor’s Chiplet Hub™ for its Safety-Critical mSoC™ Platform Designed Ground-up for Autonomy
- Axelera AI Secures up to €61.6 Million Grant to Develop Scalable AI Chiplet for High-Performance Computing
- BOS Semiconductors Signed Development Contract for ADAS Chiplet SoC with an European OEM
- Ayar Labs Unveils World's First UCIe Optical Chiplet for AI Scale-Up Architectures
Latest News
- Arteris Network-on-Chip Technology Achieves Deployment Milestone of 4 Billion Chips and Chiplets
- Empower Introduces High-Density Embedded Silicon Capacitors to Advance Next-Generation AI and HPC Performance
- AI Elevates Production Management’s Importance in the ASIC Value Chain
- Omni Design Technologies Advances 200G-Class Co-Packaged Optics IP Portfolio for Next-Generation AI Infrastructure
- Tower Semiconductor Teams with NVIDIA to Advance AI Infrastructure with 1.6T Data Center Optical Modules