Vladimir C.
Computer Vision Engineer
Volodymyr is a seasoned Deep Learning & Computer Vision Engineer with deep expertise in Generative AI and media synthesis. In recent years, he has specialized in architecting complex systems from the ground up-ranging from developing Image-to-Video and Lipsync modules to deploying scalable services powered by Stable Diffusion. His background covers the entire ML product lifecycle, from initial R&D and model training in PyTorch to deep inference optimization using TensorRT and ONNX for real-time applications. Throughout his career, Volodymyr has successfully delivered high-impact, technologically sophisticated projects, including AI-driven content creation platforms, 3D head reconstruction systems, and real-time analytical solutions for sports broadcasting and fitness. He is highly proficient with the Diffusers library and has extensive experience with Image-to-Mesh pipelines and complex multi-object tracking. Beyond model development, he places a strong emphasis on infrastructure and MLOps (Docker, ClearML, DVC), ensuring the stability and reproducibility of experiments in production environments. His primary focus is striking the perfect balance between high-fidelity generation and system performance. Volodymyr excels at optimizing GPU memory consumption and accelerating neural networks, enabling the deployment of heavy models under high-load conditions or on edge devices without compromising quality.
Key Expertise
Experience
+8 years
Timezone
CET (GMT +1)
1. Generative AI Video Platform (Lipsync & Video Generation)
Project overview:
Development of a large-scale generative AI video platform serving high-volume content creation, architecting image-to-video and video-to-video systems from scratch.
Responsibilities:
- Owned and led lipsync research and development direction
- Designed architecture for audio-driven facial animation models
- Developed and trained deep learning models
- Optimized inference performance and GPU memory usage
Achievements:
• Launched a production-ready lipsync module with high realism • Improved temporal consistency and generation stability • Successfully integrated models into the production pipeline
2. Image Generation Service based
Project overview:
Built a scalable production image generation service based on Stable Diffusion capable of handling user-level traffic.
Responsibilities:
- Integrated diffusion models into backend systems
- Performed GPU and memory optimization
- Developed REST API for generation services
Achievements:
• Deployed scalable image generation API • Optimized GPU usage and inference speed • Reduced infrastructure cost per generation
3. AI-Based Fitness Technique Correction App
Project overview:
Developed a real-time fitness application that analyzes exercise technique using a camera. Users select an exercise, position the camera, and receive feedback on movement correctness.
Responsibilities:
- Built pose estimation pipeline
- Developed biomechanics-based movement evaluation algorithms
- Compared user motion against reference templates
- Optimized models for real-time inference
Achievements:
• Implemented real-time exercise technique evaluation • Reduced user technique errors through AI-based feedback • Achieved low-latency performance suitable for mobile devices
4. Real-Time Football Match Perception System
Project overview:
Led the end-to-end development of a real-time computer vision system for football match analytics, combining OCR, object detection, tracking, classification, and classical CV techniques into a unified production pipeline.
Responsibilities:
- Developed object detection and player tracking models
- Implemented OCR for scoreboard and broadcast overlays
- Designed a modular perception architecture for real-time inference
- Built and maintained the data labeling and validation pipeline
- Optimized system performance for stable real-time execution
Achievements:
• Built a low-latency multi-module perception system operating in real time • Successfully combined deep learning and classical CV methods in a single pipeline • Reduced processing delay while maintaining high detection accuracy • Enabled automated extraction of structured match data from live video streams
5. Smart Parking Detection System
Project overview:
Designed a system that detects available parking spaces from live camera feeds.
Responsibilities:
- Developed vehicle detection model
- Performed geometric calibration of parking zones
- Implemented occupancy status logic
- Optimized for edge-device deployment
Achievements:
• Implemented real-time occupied/free parking spot detection • Improved robustness under varying lighting conditions • Prepared system for integration into urban infrastructure
Key Expertise
Experience
+8 years
Timezone
CET (GMT +1)
Ready to Work with Vladimir C.?
Computer Vision Engineer
Share your project details and our team will review the match and confirm availability.
We respond within 24 hours.