Location
PolandRate
Years of experience
8+About
I am a Computer Vision Engineer based in Krakow, Poland, specializing in Computer Vision, Deep Learning, and Machine Learning. Throughout my career, I have worked on various projects, including Object Detection, Face Recognition, and Domain Adaptation. My recent experience includes my role at Glimpse Analytics, where I created Docker images, prepared validation datasets, and optimized models. I also led a team at EzSpeech, where I conducted technical interviews, optimized code, and improved the data acquisition process. At Epam Poland, I handled technical interviews, data collection for Object Detection tasks on Jetson Nano, and led a project to speed up rendering processes. In previous roles, I contributed to diverse projects, from GAN-based synthetic data generation at Umojo, Inc to improving face swap pipelines at Dowell / Everypixel. At MaritimeAI.Net, I implemented a sonar image generation pipeline and researched underwater dehazing techniques. I have also worked on various freelancing projects, developing pipelines for 3D head generation from single images and creating databases of Deep Fake videos. My technical expertise includes Python, Bash, C#, C++, Unity, Unreal Engine, Git, Docker, and Blender. Additionally, I am a candidate master in chess, demonstrating my strategic thinking and problem-solving skills.Tech Stack
OpenCV, Bash, C#, C++, Python, Unity3DExperience
- Created Docker images to run the core library within OpenVINO dependencies requirements.
- Utilized OpenCV as a primary technology for various computer vision tasks, including image processing, object detection, and feature extraction, enhancing project outcomes and performance.
- Led a team of four developers, ensuring timely delivery of tasks and optimizing code for facial parsing algorithms.
- Implemented and optimized computer vision algorithms using OpenCV for tasks such as image segmentation, object tracking, and face recognition, significantly improving model accuracy and efficiency.
- Collected data for Object Detection and Tracking tasks for deployment on Jetson Nano devices and led projects to accelerate rendering processes.
- Developed a GAN pipeline to generate realistic synthetic data for training purposes in rare object detection use cases.
- Implemented a sonar image generation pipeline using GANs, significantly improving object detection quality by 14%.
- Created a full pipeline for 3D head generation from a single image and developed a database of Deep Fake videos using advanced deep learning techniques.
- Trained GANs to create synthetic datasets for face identification, improving the face identification model's quality by 25%.
Employment history
• Making a Docker image to run Core library inside within the Openvino dependencies requirements
• Preparing validation datasets for Detection and Tracking algorithms in MOT format
• Preparing training datasets from customer’s data for custom Detection and Classification use cases, and training and validating models on them
• Models conversion, optimization and delivery
• Research on a more accurate Tracking algorithms with checking them on customers’ videos
• Core code refactoring
• Team Leading of a team of 4 developers – delivering tasks
• Conducting technical interviews on Computer Vision Engineer and Backend Engineer positions
• Code refactoring
• Code optimization
• Checking and testing new approaches for facial parsing algorithms
• Making data acquisition process faste
• Conducting technical interviews on Data Scientist, Machine Learning Engineer, Computer Vision Engineer positions
• Collecting data for Object Detection and Tracking tasks for running at Jetson Nano device
• Making Knowledge Transfer sessions with short explanation of modern approaches related to business problems
• Providing presales materials
• Team leading a project related to faster rendering
• Making a lot of research about suitable approaches and datasets
• Hiring people on positions of Computer Vision Engineer, Speech Recognition Engineer, Chatbots Developer
• Conducting technical interviews on the positions listed above
• Collecting data for training purposes on some rare use cases for object detection task
• Making GAN pipeline for making synthetic data realistic
• Working on data pipelines
• Research on 3d rendering and Gans staff
• Developing and implementing machine learning algorithms to improve data analysis and prediction accuracy.
• Collaborating with cross-functional teams to integrate machine learning solutions into existing systems and workflows.
• Dataset preparation for GAN training – data download, parsing and filtering
• GAN models research
• Preparing datasets for GAN training, including downloading, parsing, and filtering data to ensure high-quality inputs.
• Conducting research on GAN models, exploring new techniques and methodologies to improve model performance.
GAN models research
Preparing datasets for GAN training, including downloading, parsing, and filtering data to ensure high-quality inputs.
Conducting research on GAN models, exploring new techniques and methodologies to improve model performance.
• Research and enhancement of current pipeline for face swap – working on making high resolution of face swap
• Research of face detection and landmarks detection frameworks concerning their inference time on different servers
• Researching and enhancing the current pipeline for face swap, focusing on achieving high-resolution face swaps.
• Investigating and evaluating various face detection and landmarks detection frameworks, optimizing inference times across different servers.
• Implementing a sonar images generation pipeline with GANs – the use of synthetic dataset improved quality of object detection for 14%
• Doing research on underwater dehazing pipelines
• Training a multi-class segmentation baseline for ice ground segmentation
• Working on video superresolution baseline research
• Exploring and rum demos on baseline networks for 3d multi-view reconstruction
• Doing research about pipelines on object detection for ARM processors
• Training several GAN models for response text generation in the Russian and English languages
• Working on optimization of inference time – current model in production works 2.5 times faster than the previous one
• Making a model of paragraph sentence ratio with 80% AUC quality
• Developing a pipeline of based on insight face
• Creating a full pipeline of 3d head generation from one single image
• Creating a database of Deep Fake videos using various deep learning techniques from downloaded and splitted Youtube videos
• Research of applications, light-weighted neural networks and frameworks for age/race/gender detection on ARM processors
• Researching and compiling a demo of application for gaze detection
• Training GANs for making synthetic datasets for face identification (standard models don’t work because of camera distortion)
• Training face identification model on prepared data and implementing it to current framework
• Training Object Detection model on satellite imagery Improved quality of face identification model to 25%.
• Improving the quality of face identification models by 25% through continuous research and model optimization.
• Domain Adaptation with GANs to provide data of various weather conditions for training models. It has helped to improve a quality of Detection and Instance Segmentation models up to 30% in night and rain weather conditions
• Preparing data for training Classifier model of 200 classes (overmapped existed classes and got statistics of them)
• Training models for Instance Segmentation task
• Making internal tools to Data Science team for better obtaining data for training models
• Kaggling a lot at free time (Data Science Bowl -Top14%, Camera Identification Challenge – Top39%, models for WAD CVPR Challenge (segmentation)
• Developing and implementing game features and mechanics using Unity and Unreal Engine, contributing to the overall gameplay experience.
• Designing and creating sound effects and audio assets to enhance the gaming experience, ensuring high-quality audio integration.
• Collaborating with the design and development team to refine game elements and resolve technical issues, ensuring seamless gameplay.
• Conducting testing and debugging to identify and fix bugs, optimizing game performance and stability.