Hybrid Data Scientist: ML Pipelines & Feature Engineering

ITDS; Kraków; Hybrid; PLN 120,000 - 180,000; Full time

Benefits offered by this job

Medical Package

Multisport Program

Social Events

Job summary

ITDS is seeking a Mid-Level Data Scientist in Kraków for a hybrid role (2 days in office, 3 days remote). You will develop and optimize ML pipelines, perform feature engineering, and collaborate with data teams to drive impactful insights.

Ideal candidates have 3+ years in ML pipelines, hands-on with XGBoost, LightGBM, MLP, autoencoders, SQL and Python (PySpark, pandas); knowledge of Apache Spark is a plus. EU work eligibility required.

Qualifications

• 3+ years of experience in classical ML pipelines.
• Hands-on experience with feature engineering and models (XGBoost, LightGBM, MLP, autoencoders).
• Advanced SQL skills and Python APIs (PySpark, pandas).

Responsibilities

• Support the ML team with feature engineering, model selection, training, validation, and testing.
• Analyze datasets to evaluate their suitability and contribution to projects.
• Collaborate closely with data scientists and data engineers to enhance pipeline performance.

Skills

ML pipelines

Feature engineering

SQL

Python APIs

PySpark

pandas

Tools

XGBoost

LightGBM

MLP

Autoencoders

Apache Spark

Job description

ITDS is seeking a Mid-Level Data Scientist in Kraków for a hybrid role (2 days in office, 3 days remote). You will develop and optimize ML pipelines, perform feature engineering, and collaborate with data teams to drive impactful insights.

Ideal candidates have 3+ years in ML pipelines, hands-on with XGBoost, LightGBM, MLP, autoencoders, SQL and Python (PySpark, pandas); knowledge of Apache Spark is a plus. EU work eligibility required.