Kirill Solodskih, Co-Founder and CEO of TheStage AI – Interview Series

[mouakter14]

Search
interviewsKirill Solodskih, Co-Founder and CEO of TheStage AI – Interview Seriesmmupdated on April 15, 2025By Antonio Tardif
Kirill Solodskih , PhD, is the co-founder and CEO of TheStage AI, as well as an experienced AI researcher and entrepreneur with over a decade of experience optimizing neural networks for real-world business applications. In 2024, he co-founded TheStage AI , which raised $4.5M in funding to fully automate neural network acceleration on any hardware platform.

Previously, as a Team Lead at Huawei, Kirill led the acceleration of camera AI applications for Qualcomm NPUs, contributing to the performance of the P50 and P60 smartphones and earning multiple patents for his innovations. His research has been presented at major conferences such as Cvpr and ECCV , where he has received industry awards and recognition. He also hosts a podcast on AI optimization and inference.

What inspired you to co-found TheStage AI and how did you transition from academia and research to inference optimization as a startup founder?

The foundation for what became TheStage AI began with my work at Huawei, where I was deeply involved in deployment automation and neural network optimization. These efforts became the foundation for some of our breakthrough innovations, and that’s where I saw the real challenge. Training a model is one thing, but getting it to run office 365 database efficiently in the real world and make it accessible to users is another. Deployment is the bottleneck that prevents many great ideas from coming to life. To make something as easy to use as ChatGPT, there are a lot of backend challenges involved. From a technical perspective, neural network optimization is about minimizing parameters while maintaining high performance. It’s a complex mathematical problem with a lot of room for innovation.

Manual inference optimization has long been a bottleneck in AI. Can you explain how TheStage AI automates this process and why it is a game changer?

TheStage AI addresses a major bottleneck in AI: manual compression and acceleration of neural networks. Neural networks have billions of parameters, and manually figuring out which ones to remove to improve performance is nearly impossible. ANNA (Automated Neural Networks Analyzer) automates this process, identifying which layers to exclude from optimization, similar to how ZIP compression was first automated.

This is a game changer, making AI adoption faster and cheaper. Instead of relying on expensive manual processes, startups can optimize models automatically. The technology gives companies a clear view of performance and costs, ensuring efficiency and scalability without uncertainty.

TheStage AI claims to reduce inference costs by up to 5x: what makes your optimization technology so effective compared to traditional methods?