Igor Kołodziej

I build software for quantitative and data-intensive problems.

MSc student in Data Science at Warsaw University of Technology, with experience in statistical software development, quantitative modeling and backend systems.

CV (PDF) Email GitHub LinkedIn

Selected work

Python · scikit-learn · Optuna

Mamut Model selection and evaluation for tabular classification

Co-author and maintainer of a Python toolkit for transparent tabular-classification workflows.

  • Keeps candidate-specific preprocessing and Optuna tuning inside validation, with optional nested and group-disjoint selection.
  • Challenges the selected model with leakage checks, fixed baselines and repeated-CV stability evidence.
Project note PyPI Documentation Source

Scala · Redpanda · PostgreSQL · MongoDB

Payment Event Pipeline Event-processing backend in Scala

Co-developed a payment-event pipeline with replay and broker-backed inputs, customer-data enrichment, deterministic decisions and persistent processing history.

  • Uses functional streaming and replaceable adapters to separate processing from infrastructure.
  • Adds idempotent persistence, automated tests and reproducible local infrastructure.
Project note Source
More projects
Aegis — cross-project incident response platform on GCP, connecting logs, Pub/Sub, Cloud Run, Slack and Terraform-managed infrastructure. Source
Real-Time Finance Pipeline — crypto and FX data pipeline with Kafka, HDFS, Spark, Hive and HBase. Source
DoomRL — PPO/A2C reinforcement-learning agents for ViZDoom. Source
DermNet — image clustering with DINOv2 embeddings, UMAP and agglomerative clustering. Source

Experience

Goldman Sachs

Summer Analyst — Counterparty Credit Risk Strats

–

Developed quantitative modeling software and designed Monte Carlo validation experiments for counterparty exposure.

Poznań University of Economics and Business

Research Software Engineer

–

Co-developed NMAR within an NCN OPUS 20 research project and presented the work at uRos 2025 and ElementsX 2025.

Accenture

Data Engineer Intern

–

Maintained and extended an SAP BW data warehouse, investigated data issues and implemented fixes and enhancements in ABAP.

About

Education

Warsaw University of Technology

  • MSc Data ScienceExpected
  • BEng in Data Science · Final grade 5.0/5.0

Technical focus

Statistical computing, quantitative modeling, model evaluation and backend systems.

Python, Java, R, SQL and Scala.

Leadership & distinctions
– President, Data Science Club at WUT — led a student team organizing talks, workshops and projects, with guests from Google, ING and Allegro.
– Co-organizer, ensembleAI hackathon — sponsors, logistics, venue coordination and on-site operations.
– Capitalize — built FastAPI backend features and analyzed usage metrics for a financial-literacy app released to a Google Play testing track. The student venture placed 2nd at the Enactus Poland National Competition 2023.
Laureate, AGH “Diamond Index” Olympiad in Physics.
Finalist, National Technical Knowledge Olympiad.

Contact

CV (PDF) Email GitHub LinkedIn