Senior Machine Learning Engineer

Ubique Systems; Helsinki; On-site; EUR 90,000 - 130,000; Full time

Job summary

Ubique Systems is seeking an experienced Senior Machine Learning Engineer to design, implement, deploy, and optimize ML models for customer analytics and recommendation systems in a data-driven environment.

You will develop end-to-end predictive models for churn, upsell/cross-sell, CLV, and next-best-action recommendations, leveraging Python, SQL, PySpark, and AWS cloud technologies within MLOps pipelines.

Qualifications

• 5+ years of experience in Machine Learning Engineering or Data Science.
• Strong hands-on experience in Python, SQL, and PySpark.
• Experience developing and deploying end-to-end ML models.
• Practical experience in customer analytics and recommendation systems.
• Experience with AWS cloud and scalable ML pipelines.
• Knowledge of MLOps, model monitoring, and production deployment.

Responsibilities

• Develop, train, validate, and deploy ML models for customer churn, upsell, cross-sell, downsell, and customer lifetime value prediction.
• Build next-best-action recommendation and ranking models.
• Define model targets, labels, prediction horizons, and customer eligibility criteria in collaboration with business teams.
• Perform feature engineering, feature selection, exploratory analysis, and data leakage assessment.
• Build scalable feature stores and point-in-time-correct training and scoring datasets.
• Develop NLP and sentiment-based features from customer feedback and free-text data.
• Implement model validation, probability calibration, and class imbalance handling.
• Monitor model performance and stability across customer segments and time periods.
• Develop scalable ML pipelines using modern MLOps frameworks.

Skills

Python

SQL

PySpark

AWS

MLOps

Machine Learning

Deep Learning

Predictive Modeling

Churn Prediction

Recommendation Systems

Tools

MLflow

Kubeflow

SageMaker

Job description

We are looking for an experienced Senior Machine Learning Engineer with 5+ years of experience in developing, deploying, and optimizing machine learning models for customer analytics and recommendation systems.

The candidate will be responsible for building predictive models for customer churn, upsell/cross-sell propensity, customer lifetime value (CLV), revenue contraction, and next-best-action recommendations. The role requires strong expertise in Python, SQL, PySpark, AWS cloud, machine learning, and MLOps frameworks.

Key Responsibilities:

• Develop, train, validate, and deploy ML models for customer churn, upsell, cross-sell, downsell, and customer lifetime value prediction.
• Build next-best-action recommendation and ranking models.
• Define model targets, labels, prediction horizons, and customer eligibility criteria in collaboration with business teams.
• Perform feature engineering, feature selection, exploratory analysis, and data leakage assessment.
• Build scalable feature stores and point-in-time-correct training and scoring datasets.
• Develop NLP and sentiment-based features from customer feedback and free-text data.
• Implement model validation, probability calibration, and class imbalance handling.
• Monitor model performance and stability across customer segments and time periods.
• Develop scalable ML pipelines using modern MLOps frameworks.

Required Technical Skills:

• Programming: Python, SQL, PySpark.
• Machine Learning: Machine Learning, Deep Learning, Predictive Modeling, Model Training and Validation.
• ML Use Cases: Churn Prediction, Propensity Modeling, Customer Lifetime Value, Recommendation Systems.
• AWS & Data Engineering: AWS S3, Data Lake/Lakehouse Architecture.
• MLOps: MLflow, Kubeflow, AWS SageMaker, or equivalent frameworks.

Experience & Qualifications:

• 5+ years of experience in Machine Learning Engineering or Data Science.
• Strong hands-on experience in Python, SQL, and PySpark.
• Experience developing and deploying end-to-end ML models.
• Practical experience in customer analytics and recommendation systems.
• Experience with AWS cloud and scalable ML pipelines.
• Knowledge of MLOps, model monitoring, and production deployment.
• Strong analytical and stakeholder collaboration skills.