At Shoptimus AI, we are revolutionizing the weekly grocery run. We are a B2B startup providing leading supermarkets with a smart shopping assistant designed to maximize customer loyalty.Our technology doesn't just fill a cart; it understands the household. Our models predict weekly needs before the customer realizes them and automatically generate complete shopping lists. We help users discover relevant products—from personalized offers to locally sourced (Km0) items or products that fit their specific habits.Your MissionWe are looking for a Machine Learning Engineer with strong expertise in data engineering and modeling to take our prediction and recommendation systems to the next level.You will join an environment where data flow is critical. Your main goal will be to optimize, maintain, and evolve our Machine Learning pipelines on Databricks, ensuring that demand forecasts and product recommendations are accurate, scalable, and delivered to our application on time.🛠 Tech StackYou will work daily with:Language: Python (Expert), PySpark.Platform: Databricks (Workflows, Unity Catalog, model serving).Modeling: LightGBM (distributed on Spark), Sklearn.MLOps: MLflow (logging, versioning, and lifecycle management).Database: MongoDB (serving layer).🎯 What will you do?Advanced Modeling: Develop and fine-tune demand prediction models (Time Series forecasting at the household level) and personalized recommender systems.ML Engineering on Spark: Implement and optimize LightGBM models in a distributed environment using Spark, ensuring efficiency in both training and inference times.End-to-End Pipelines on Databricks:Maintain and build ETL workflows for data ingestion and feature engineering.Orchestrate batch scoring processes to generate massive predictions.Data Integration: Manage the efficient export of scoring results to MongoDB for real-time consumption by the App.MLOps & Quality: Use MLflow to manage the model lifecycle, monitor data drift, and ensure experiment reproducibility.🎓 What are we looking for?Experience: Minimum 2 years in a Machine Learning Engineer or Data Scientist role with a strong engineering component.Python & Spark: Advanced command of Python and proven experience processing large datasets with Apache Spark (PySpark).Modeling: Solid knowledge of Gradient Boosting algorithms (LightGBM, XGBoost) and recommendation techniques.Databricks: Previous experience working within the Databricks ecosystem (Notebooks, Jobs, Delta Lake).Software Engineering: Clean, modular, and testable code. Strong grasp of Git and development best practices.Languages: Professional proficiency in English (written and spoken).A note on requirements: We know the "perfect" candidate doesn't exist. If you are passionate about data and our mission, but don't meet every single requirement listed above, please apply. We’d love to hear your story and see how we can grow together.⭐ Nice to havePrevious experience in the Retail or E-commerce sector.Knowledge of MongoDB query structure and optimization.Data Visualization: Experience creating dashboards (e.g., Databricks SQL, Streamlit, or Tableau) to visualize model metrics and business KPIs.Generative AI: Interest or experience with LLMs and GenAI (e.g., RAG architectures, LangChain, or Hugging Face) for potential future features in the shopping assistant.🎁 What do we offer?A role with direct impact on a product used by thousands of families.Work with a modern tech stack (Databricks, Spark, MLflow) and real, high-volume data.Remote/Hybrid Culture: We support a hybrid or remote working model, allowing you to work from where you are most productive.Growth: A dynamic startup environment where your technical decisions matter.