Tomáš Juřica

Prague & Brno, Czech Republic · +420 774 989 814 · tomasjuri@gmail.com

Machine Learning and Computer Vision Engineer with 7+ years of experience turning AI research into real-world products. I have worked in both global corporations and agile startups, taking projects from initial research through model design, training, optimization for target hardware, deployment to customers, and ongoing monitoring.

I specialize in deep learning, embedded AI, and computer vision, with hands-on expertise in TensorFlow, PyTorch, OpenCV, CUDA, Docker. I fully leverage LLM tools to boost productivity, accelerate experimentation, and deliver results faster.

Curious by nature and not afraid of technical challenges, I am committed to continual learning and applying AI in innovative ways. I am seeking a challenging project in LLMs where I can apply and expand my skills.

Experience

Machine Learning Engineer

Veracity Protocol

Python C++ PyTorch TensorFlow OpenCV NumPy pandas TensorRT ONNX NVIDIA Jetson FastAPI Flask Docker Docker Compose AWS S3 HDR Pipeline Camera Calibration MongoDB Linux Git Grafana

Veracity Protocol develops computer vision algorithms for visual verification and authentication of physical objects based on their microstructure. You capture a photo of an ID card and it tells you if it's authentic.

As a member of the AI team, I primarily researched, developed and deployed deep learning models (like ResNet, VGG, ArcFace, transformer-based models, as well as custom architectures). Being a startup, my expertise covered the entire ML pipeline from data processing and dataset preparation to deep learning model training, deployment, and integration. I also have experience with project ownership, deployments for customers, and maintenance and updating (Docker, AWS, S3, Grafana, etc.).

One of my biggest projects was leading the development and deployment of a large-scale hardware scanner solution for collectible cards authentication for a Fortune 500 US customer, managing the complete project lifecycle.

I also presented solutions for PCB authentication and physical tampering detection at a customer conference in San Francisco, demonstrating the commercial impact of our technology and successfully delivering the POC.

I regularly created extensive datasets and managed large-scale data collection efforts for training AI models. My work also involved implementing data augmentation and smart filtration pipelines to ensure high data quality.

I optimized models with TensorRT and ONNX for high-performance inference and specifically optimized code for NVIDIA Jetson embedded platforms. I designed camera systems for production environments. Utilizing my hardware skills, I built a variety of hardware camera solutions running our computer vision pipelines at customers' premises.

Mar 2019 – Jul 2025

Computer Vision & Machine Learning Engineer

Innovatrics

Python TensorFlow PyTorch Keras Face Recognition Biometric Identification Computer Vision Automated Visual Inspection Defect Detection OpenCV NumPy pandas scikit-learn TensorBoard Mask R-CNN U-Net Docker Linux Git

As a core member of the AI research team, I contributed to the development of state-of-the-art face recognition algorithms and biometric identification systems using deep learning frameworks (TensorFlow, PyTorch, Keras). My responsibilities encompassed the entire machine learning pipeline, from implementing data processing workflows and managing datasets to deep learning model optimization and deployment.

I then joined a new team focused on automatic visual inspection, where we transitioned computer vision technology from research to production and manufacturing applications. One of my key contributions was implementing and optimizing Mask R-CNN models for defect detection in ID cards or semantic segmentation of pavement cracks.

This work involved extensive development of CNN segmentation and detection algorithms, creating custom dataset management tools, and building custom annotation frameworks specifically designed for the given tasks.

Jan 2017 – Feb 2019

Computer Vision Engineer

NXP Semiconductors

C/C++ OpenCL GPGPU OpenCV Stereo Vision 3D Reconstruction CMake Linux Bash Git Cross-compilation

My main responsibility was the implementation and optimization of computer-vision algorithms for embedded processors such as i.MX6 and i.MX8, primarily targeting ADAS applications. I focused on developing efficient algorithms using OpenCL (GPU) that could leverage the limited computational resources of embedded systems while integrating with camera interfaces.

My biggest achievement was developing an optimized stereo-vision algorithm for depth estimation and 3D reconstruction applications, achieving state-of-the-art real-time FPS performance on an embedded GPGPU. This work involved low-level C++ optimization techniques and parallel computing strategies to maximize performance on resource-constrained hardware.

Jul 2016 – Dec 2017

Education

Brno University of Technology, Faculty of Information Technology

Master of Science – Embedded Systems

Thesis: Machine-learning visual inspection and defect-detection in manufacturing.

Sep 2016 – Jun 2019

Brno University of Technology, Faculty of Information Technology

Bachelor of Science – Computer Science

Bachelor thesis: "Vehicle speed measurement using a stationary camera". I joined the faculty's research team and contributed to the development of a computer-vision system for measuring vehicle speeds.

Sep 2013 – Jun 2016

Awards & Certifications

Skills

Programming Languages & Tools

Key Competencies

Deep Learning – TensorFlow, Keras, PyTorch, ONNX, TensorRT
Computer Vision – OpenCV, Image Segmentation, Object Detection, Camera Calibration, Stereo Vision
Programming – Python, C/C++, CUDA, OpenCL, Bash, Git
Dev & Ops – Docker, Linux, AWS, Agile / Scrum
ML Engineering – FastAPI, Flask (REST inference APIs)
Classical ML & Data – scikit-learn, pandas, NumPy
Edge Deployment – NVIDIA Jetson SDK, DeepStream
Infrastructure – Docker Compose, AWS S3 / Lambda / SageMaker
GenAI – Hugging Face Transformers, Diffusers
Detection & Segmentation – YOLO, Mask R-CNN
Computer Graphics – OpenGL, Vulkan
C/C++ Build – CMake, Conan
MATLAB – Data processing & prototyping

Languages

English – C1 (Advanced)
Czech – Native
German – B2 (Upper-intermediate)
Spanish – A1–A2 (Beginner)

Interests

Areas & Hobbies

Machine learning & artificial intelligence
Computer vision & new technologies
3D printing & CAD design – built my own open-source 3D printer from hobby-shop parts; enjoy designing hardware parts such as camera and phone holders
Sports – jogging, cycling & weightlifting
Travelling & outdoor activities

Tomáš Juřica

Prague & Brno, Czech Republic · +420 774 989 814 · tomasjuri@gmail.com

Computer-vision and machine-learning engineer focused on bringing cutting-edge CV and embedded-AI solutions from research to real-world products. Passionate life-long learner with solid academic background and hands-on experience designing, training and optimising deep-learning models for high-performance deployment. I actively leverage artificial intelligence tools (including generative AI) to maximise my productivity – efficiency is my key objective.

Experience

Machine Learning Engineer

Mar 2019 – Jul 2025

Veracity Protocol

I developed and trained machine-learning algorithms for physical-object identification and verification. Specialized in PCB defect-detection, creating CNNs for visual inspection and optimizing models with TensorRT and ONNX. Led delivery of custom camera-scanner project for US client.

Computer Vision Researcher

Jan 2017 – Feb 2019

Innovatrics

R&D team member focusing on ML models and datasets for face-recognition. Contributed to automated visual inspection projects using Mask R-CNN for IC card defect segmentation.

Computer Vision Engineer

Jul 2016 – Dec 2017

NXP Semiconductors

Implemented and optimized computer-vision algorithms for embedded processors (i.MX6, i.MX8). Achieved state-of-the-art real-time stereo-vision performance on embedded GPGPU.

Education

Brno University of Technology, Faculty of Information Technology

Sep 2016 – Jun 2019

Master of Science – Embedded Systems

Thesis: Machine-learning visual inspection and defect-detection in manufacturing.

Brno University of Technology, Faculty of Information Technology

Sep 2013 – Jun 2016

Bachelor of Science – Computer Science

Awards & Certifications

Retrieval Augmented Generation (RAG) – DeepLearning.AI (Aug 2025)

Generative AI with Large Language Models – DeepLearning.AI & AWS (Jun 2025)

Apply Generative Adversarial Networks (GANs)

Build Better Generative Adversarial Networks (GANs)

Generative Adversarial Networks (GANs)

Natural Language Processing Specialization – DeepLearning.AI

Build Basic Generative Adversarial Networks (GANs)

Natural Language Processing with Attention Models

Natural Language Processing with Sequence Models

Introduction to TensorFlow for Artificial Intelligence, Machine Learning, and Deep Learning

Natural Language Processing with Classification and Vector Spaces – DeepLearning.AI (Sep 2020)

Natural Language Processing with Probabilistic Models

Deep Learning Specialization – DeepLearning.AI

Sequence Models – DeepLearning.AI (Jan 2019)

Convolutional Neural Networks – DeepLearning.AI (Dec 2018)

Improving Deep Neural Networks – DeepLearning.AI (Dec 2018)

Neural Networks and Deep Learning

Structuring Machine Learning Projects

Skills

Programming Languages & Tools

Key Competencies

Deep Learning – TensorFlow, Keras, PyTorch, ONNX, TensorRT

Computer Vision – OpenCV, Image Segmentation, Object Detection, Camera Calibration, Stereo Vision

Programming – Python, C/C++, CUDA, OpenCL, Bash, Git

Dev & Ops – Docker, Linux, AWS, Agile / Scrum

ML Engineering – FastAPI, Flask (REST inference APIs)

Classical ML & Data – scikit-learn, pandas, NumPy

Edge Deployment – NVIDIA Jetson SDK, DeepStream

Infrastructure – Docker Compose, AWS S3 / Lambda / SageMaker

GenAI – Hugging Face Transformers, Diffusers

Detection & Segmentation – YOLO, Mask R-CNN

Computer Graphics – OpenGL, Vulkan

C/C++ Build – CMake, Conan

MATLAB – Data processing & prototyping

Languages

English – C1 (Advanced)

Czech – Native

German – B2 (Upper-intermediate)

Spanish – A1–A2 (Beginner)

Interests

Machine learning & artificial intelligence

Computer vision & new technologies

3D printing & CAD design – built my own open-source 3D printer from hobby-shop parts; enjoy designing hardware parts such as camera and phone holders

Sports – jogging, cycling & weightlifting

Travelling & outdoor activities