Python is my primary programming language and I like to work with tools such as Typing, Poetry, Black, and pytest.

Pandas is my favourite framework for data cleaning and data processing and I use it in all projects I work in.

Airflow has become my go-to tool for scheduling and running data pipelines. I have worked with both managed and self-hosted solutions.

I have wide experience working with SQL for analytical purposes in different databases such as BigQuery, AWS Athena, PostgreSQL, MSSQL, DuckDB, and Snowflake.

scikit-learn is my prefered tool for classic machine learning models such as linear / logistic regression, random forest, k-mean clustering, and dimension reduction models such as T-SNE.

I have worked with several different Deep Learning frameworks such as Keras, Tensorflow, Tensorflow Lite, and PyTorch.

Tableau, Metabase, Plotly, Klipfolio, and Streamlit are some of the tools I’ve used when visualizing data.

I have fine-tuned a GPT-2 model on music lyrics, built a ChatPDF application using Vicuna models, and generated images using Stable Diffusion.

I usually work closely with stakeholders and often help with converting business requirements into technical requirements. I have had the role as tech-lead for smaller teams.