> Markdown version of [/jobs/ext/3303697-data-scientist](https://www.wearedevelopers.com/jobs/ext/3303697-data-scientist). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# DATA SCIENTIST

- **Company:** Canyon Bicycles GmbH
- **Location:** Koblenz, Germany
- **Experience:** Experienced
- **Contract:** Permanent contract
- **Skills:** Amazon Web Services, Microsoft Azure, BigQuery, Cloud Computing, Data Cleansing, Data Retrieval, Database Queries, Statistical Hypothesis Testing, Python (Programming Language), Machine Learning, Tensorflow, Google Cloud, Feature Engineering, Pytorch, Git, Pandas, Scikit Learn, Data Analytics, Xgboost, Machine Learning Operations, Software Version Control, Api Management, Unsupervised Learning
- **Published:** September 23, 2026
- **Apply:** https://www.indeed.com/viewjob?jk=abb8b3494b1a420b

## About the Role

* Educational Background: A degree in data science, data analytics, statistics, applied mathematics, or a closely related quantitative field forms your academic foundation.
 * Professional Experience: 4+ years of hands-on experience developing, deploying, and validating machine learning models in production environments within e-commerce, retail, or digital industries characterises your background.
 * Technical Stack & Tools: Advanced Python proficiency (Scikit-learn, XGBoost, PyTorch/TensorFlow, Pandas), strong SQL skills for extracting data in BigQuery, and practical experience with API integrations and Git version control set your profile apart.
 * Cloud & ML Ecosystem: Demonstrated expertise deploying models within Google Cloud Platform (Gemini Agent Platform, BigQuery ML, Meridian, Cloud Run) or equivalent environments (AWS/Azure) shapes your daily execution.
 * Statistical Mastery: A solid foundation in supervised and unsupervised learning, time-series forecasting, statistical hypothesis testing, and price sensitivity/elasticity analysis defines your analytical approach.
 * E-Commerce Expertise: Proven success delivering commercial ML use cases in e-commerce (CLV, acquisition cost optimization, pricing models, retention, personalization) drives business impact.
 * Language Skills: Excellent English communication skills (both spoken and written) enable smooth and effective collaboration across international teams and business functions.

## Description

Data is at the heart of how we grow, optimize, and innovate our e-commerce business at Canyon. As a Data Scientist in our Digital department, you build, operationalize, and scale data-driven models on Google Cloud Platform to drive customer lifetime value expansion, margin optimization, marketing mix modeling, and AI-native applications. Your data products will directly impact business operations and commercial decision-making across all global channels., * Customer Intelligence: Designing and deploying Customer Lifetime Value (CLV) models that integrate customer, transaction, engagement data, and acquisition costs leverages complex enterprise data structures.

 * Price Modeling: Building price elasticity algorithms using historical demand, inventory levels, and market signals optimizes gross margins across our bike portfolio.
 * Acquisition Channel Optimization: Defining and deploying an advanced Marketing Mix Model (MMM) through Google's Meridian framework measures and optimizes multi-channel advertising efficiency.
 * Personalization Engine: Developing personalization systems for website and marketing touchpoints utilizes customer engagement and preference data.
 * Predictive Marketing: Implementing propensity-to-buy and propensity-to-churn models fuels targeted email remarketing as well as predictive lookalike audiences across paid media channels.
 * Technical Ownership: Building operational ML workflows in Google Cloud Platform (Gemini Agent Platform, BigQuery, Python) establishes robust pipelines for feature engineering, model tracking, and automated retraining.
 * Data Preparation & Collaboration: Supporting data engineer:s hands-on with pipeline setup, data cleaning, and automation in BigQuery and dbt ensures ideal conditions for downstream model training.
 * Evaluation & Quality Assurance: Monitoring ML infrastructure and model availability includes implementing version control and maintaining transparent documentation for all data products.
 * Stakeholder Management: Partnering directly with commercial lead:s across CRM, Pricing, Sales, Performance Marketing, and E-Commerce translates business challenges into quantitative models with clear commercial targets.