ML engineering / Cybord AI
Powerful models. A practical desktop experience.
Bringing proprietary AI models into a production desktop app with real-time inference.
01 →Desktop interface
02 →FastAPI backend
03 →Model workers
04 ✓Real-time results
The challenge
An AI model is only part of a usable product. This project needed a desktop interface, a reliable backend, and an inference pipeline that could run proprietary models quickly enough for real-time use in an enterprise setting.
The engineering
- Built the production desktop application with Electron and a FastAPI backend.
- Integrated proprietary AI models using PyTorch and a multiprocessing inference pipeline.
- Optimized model inference as part of the broader production inspection workflow.
The result
-60%
Shipped a production desktop application integrating real-time AI inference. Model inference time was reduced by 60%.
05.Open a connection
open to interesting problems
Production ML, computer vision, AI infrastructure, or a team looking for an engineer who ships. Tell me what you have in mind. Three fields, one conversation.
Fill out the form → hit send → I’ll reply to your email.
↓ download résumé · PDF