Data Engineer & Data Scientist & Python Developer

Uchazeč je datový vědec se silným technickým zázemím, který se specializuje na vytváření datových pipeline, vývoj modelů strojového učení a nasazování backendových řešení. Je nadšený z využívání dat k podpoře růstu podniků a má hluboký zájem o finance a startupy. Má zkušenosti s programovacími jazyky, jako jsou Python a SQL, a také s prací s databázemi, jako jsou BigQuery a AWS S3. V současné době pracuje jako inženýr strojového učení, kde vyvíjí datové toky pro zpracování videa a trénuje segmentační modely.

Machine Learning Engineer (10/2025 - present)

• The candidate developed a Django-based video processing pipeline for a belt granulometry system, enabling real-time analysis of conveyor belt material.
• Designed and trained a UNet segmentation model to detect and classify dust and ore particles from industrial video streams.
• Built end-to-end ML workflows: data annotation with Label Studio, model training with PyTorch, and production deployment on Kubernetes.
• Contributed to multiple other Django projects, delivering robust backend services and APIs across the engineering team.
• Tools: Python, Django, PyTorch, er, Kubernetes, Label Studio.

Senior Full-Stack Data Engineer (09/2019 - 10/2025)

• The candidate designed and deployed automated data pipelines, processing millions of records across various sources.
• Performed extensive data wrangling and exploratory analysis to surface business insights.
• Built machine learning models from baseline to advanced, including feature engineering and hyperparameter tuning.
• Evaluated model performance, conducted residual analysis, and improved predictive accuracy via feature importance insights.
• Delivered reports and dashboards used directly by clients for decision-making.
• Tools: Python (pandas), DuckDB, BigQuery, AWS, Google Cloud, Jupyter Notebooks, DVC, Papermill, er, Kepler.gl.

Consultant (03/2019 - 09/2019)

• The candidate built interactive behavior systems for humanoid robots used in marketing and data collection.
• Programmed autonomous charging and movement algorithms.
• Integrated speech recognition and synthesis, enabling natural language interactions.
• Created integrated data sync systems using Google Sheets, SMS, and email APIs.

Software Engineer (01/2018 - 12/2018)

• The candidate led backend engineering for the AnaCredit reporting system.
• Developed secure, reliable modules for user data ingestion and validation.
• Implemented system monitoring, logging, and retry strategies to ensure high availability.
• Built an internal admin UI and RESTful API for system users.
• Stack: Python (Django), Oracle, er.

Software Engineer (09/2017 - 01/2018)

• The candidate developed embedded firmware for GSM/GPS tracking systems.
• Wrote backend services in C++ for real-time communication protocols.
• Delivered production-grade code using STM32 development tools.