Beter1mo ago

Data Scientist

PL·Warsawmid

Data ScientistData

2 views0 saves0 applied

Apply Now

Quick Summary

Key Responsibilities

Develop and refine mathematical and statistical models for predicting sports and e-sports outcomes. Communicate with end users, collect feedback, and build technical solutions based on it.

Technical Tools

Data ScientistData

Responsibilities

~1 min read

→Develop and refine mathematical and statistical models for predicting sports and e-sports outcomes.
→Communicate with end users, collect feedback, and build technical solutions based on it.
→Apply machine learning to improve trading strategies, automate workflows, and detect anomalies.
→Proactively identify opportunities to use data science for business optimization and process automation.
→Perform large-scale historical data analysis to generate insights and improve model performance.
→Collaborate with backend engineers to build and maintain production machine learning systems.
→Research and prototype new methods for expanding into new sports and markets.

Delivery of production-ready machine learning models and pipelines for trading within agreed timelines.
Improvement in model accuracy and reliability, measured against established benchmarks.
Reduction of manual intervention in trading workflows through automation initiatives.

Requirements

~1 min read

5+ years of experience in data science, analytics, or a related field.
Proficiency in Python (pandas, numpy, scikit-learn, etc.) and working with databases.
Strong knowledge of statistical modeling, probability, and machine learning techniques (Supervised Learning, Unsupervised Learning).
Experience with XGBoost/LightGBM.
Experience with large-scale data analysis and building actionable insights.
Ability to work collaboratively in a cross-functional team and communicate results clearly.
English level - Upper-intermediate and higher.

Experience in the sports or betting industry.
Experience with PyTorch/Tensorflow.
Familiarity with real-time data processing (Kafka, streaming systems).
Exposure to building data pipelines and integrating ML models into production systems.
Knowledge of advanced ML techniques (e.g., ensemble methods, time-series forecasting, anomaly detection).