Summary
Sergey Zinchenko is a Senior Data Scientist with a decade of experience building production-grade ML systems across Computer Vision and LLMs, delivering measurable gains in Automotive, Healthcare, and Video Analytics. He specializes in end-to-end solutions—from defining requirements and data pipelines to model training, inference optimization (ONNX/TensorRT), and robust MLOps—achieving outcomes like 7.7x faster vehicle issue detection, 5x faster action-recognition inference, and +5% F1 in medical tasks. Sergey blends research-driven methods (Self-Supervised Learning, ViT, custom layers) with pragmatic engineering—accelerating training 10x and shipping MVPs on tight timelines. Comfortable leading cross-functional teams or driving projects solo, he has repeatedly turned complex, noisy data into reliable, deployed services (e.g., anti-fraud cinema systems, steel-industry vision MVPs). Based in Larnaca, Cyprus, he also leverages LLMs and RAG to automate feedback loops that surface critical issues earlier, improving operational safety.
10 years of coding experience
7 years of employment as a software developer
Bachelor's degree, Computer Science, Bachelor's degree, Computer Science at Southern Federal University (former Rostov State University)
English, Russian