Job Opportunity:
Cat Digital is expanding its operations and opening a new branch in Slovakia. We are seeking talented individuals to join our team to help us establish and grow our presence, organization, culture, which will drive our digital product development efforts. As a member of our team, you will have the opportunity to work with cutting-edge technologies and collaborate with top professionals working on very high impact and visibility products. Don't miss this chance to join and support digital innovation for a global leader in heavy machinery!
What will you do?
As a Junior Data Scientist at Cat Digital's Slovakian branch, you will contribute to design, development and deployment of Caterpillar’s state of the art digital program. You will also:
- Contribute to anomaly detection and prediction capabilities, focusing on noise reduction and model improvements.
- Package models as analytics ready outputs (exception triggers, scores, confidence, salient channels) and integrate with data lake pipelines for delivery to the Foresight UI (CAT’s in-house monitoring solution).
- Partner with product & application teams to wire model outputs into Suggested/Auto Recommendations and Enhanced Analytic Context in CMA workflows.
- Build reproducible training/evaluation pipelines; contribute to MLOps (data versioning, model registry, CI/CD, monitoring, drift checks).
- Track key metrics (precision/recall, exception noise, lead time, coverage) and participate in feedback driven retraining using CMA and recommendation signals.
This position works directly with Slovakia based engineering leadership and Cat Digital IT in the US.
What you have:
- Effective Communications: Understanding of effective communication concepts, tools and techniques; ability to effectively transmit, receive, and accurately interpret ideas, information, and needs through the application of appropriate communication behaviors.
- Relevant degree in Computer Science or similar field.
- Solid Python (pandas, NumPy), PyTorch or TensorFlow, and SQL skills; comfort with notebooks and code reviews.
- Hands-on experience with timeseries machine learning and strong interest in Attentional/Transformer methods for sequential data.
- Familiarity with model evaluation beyond accuracy (e.g., class imbalance, precision/recall, calibration, lead time).
Top candidates will have:
- Experience with Snowflake (or similar cloud data warehouse), Airflow/MLflow, Docker/Kubernetes, Grafana/Power BI.
- Knowledge of interpretability techniques for sequential models (feature/step attributions, attention visualization).
