Data Scientist (CDC)

<h3>Requirements</h3><ul>
<li>Proficiency in<strong>Python and PySpark</strong>for data analysis, machine learning, and<strong>demand forecasting</strong>(regression + time series models)</li>
<li>Experience with forecasting models such as<strong>LightGBM/ XGBoost</strong>and classical time series methods (e.g.,<strong>ETS/ARIMA</strong>)</li>
<li>Strong understanding of the machine learning workflow (<strong>data cleansing, feature engineering, model evaluation, model explainability</strong>)</li>
<li>Familiarity with forecasting evaluation metrics (e.g.<strong>MAPE, MAE</strong>) and ability to validate model performance</li>
<li>Strong<strong>SQL</strong>skills for managing and querying large datasets</li>
<li>Knowledge of data visualization tools (e.g.,<strong>Power BI</strong>)</li>
<li>Experience with cloud-based technologies such as<strong>Databricks, Azure, or AWS</strong>
</li>
<li>Strong communication skills — able to explain insights and models to both business and technical teams</li>
<li>Ownership and accountability — able to deliver end-to-end solutions, not just analysis</li>
<li>Collaboration — able to work effectively with<strong>Data Engineering, Tech, Product, and Supply Chain</strong>teams</li>
</ul><h2>Preferred (Optional) Qualifications:</h2><ul>
<li>Exposure to MLOps tools (e.g.,<strong>MLflow</strong>, job scheduling)</li>
<li>Experience building production pipelines for forecast outputs (daily/weekly runs) and supporting downstream systems</li>
<li>Experience in real-time analytics or scheduled processing systems</li>
<li>Optimization mindset — able to balance accuracy, business impact, and time constraints</li>
</ul><h2>Benefits</h2><ul>
<li>Clear focus.</li>
<li>Diverse Workplace (Our members are from around the world!)</li>
<li>Non-hierarchical and agile environment</li>
<li>Growth opportunity and career path</li>
</ul>