Building solutionspowered by AI
Machine learning, computer vision and language models in Python. From raw data to a model that works.
Client work
Websites and deployments built for clients.
What I do
AI and machine learning
I build predictive models on real data: cleaning the dataset, engineering features, training and tuning, then evaluating what actually came out. Python with Scikit-learn, Pandas and TensorFlow.
Computer vision and NLP
Object detection on video footage with YOLOv8, and content analysis built on natural language processing. I treat language models as a tool for a specific job, not as the point in themselves.
Studies and organisations
ICT at AGH UST in Krakow: networks, data transmission and system security. At BEST AGH Krakow I help run BITEhack - designing tasks, handling jury communication and building the event website.
Away from the terminal
Gym, running and swimming. Training regularly keeps both the body and the head in order.
Open Source
Projects built and released publicly.
Credit default prediction on the Kaggle GiveMeSomeCredit dataset: data cleaning, feature engineering, model training and evaluation.
Finds the segments of a long video most likely to work as short-form clips, combining transcription with NLP scoring of the transcript.
Vehicle detection and recognition on road footage with a fine-tuned YOLOv8 model, covering dataset preparation and inference on video.
Web application generating trading signals from market data pulled over a REST API, with a Java backend and a browser front end.
Channel open
Let's build something with your data.
I am interested in AI and machine learning work: deployments for companies, internships, research and open source. If you have data and a question it should answer, get in touch.
Get in touch