Senior Data Scientist

INSPIRE | EXHILARATE | DELIGHT For over seven decades, Chalhoub Group has been a partner and creator of luxury experiences in the Middle East. In its pursuit to excel as a hybrid luxury retailer, the Group has curated a portfolio of over 10 owned brands and strengthened its distribution and marketing expertise for over 400 international names across luxury fashion, beauty, jewellery, watches, eyewear, and art de vivre categories. Every step at Chalhoub Group is taken to build a future where luxury dreams become reality — bridging cultures and crafting memorable experiences for our consumers. Be it by constantly reinventing itself, committing to innovation, or embracing new technologies, the Group is shaping the future of luxury retail. It delivers seamless omnichannel experiences across more than 950 stores, online platforms, and mobile apps. Driving this innovation journey is The Greenhouse — the Group’s innovation hub, incubator, and accelerator for startups and emerging businesses, regionally and globally. Chalhoub Group fosters a people-at-heart culture rooted in diversity, equity, and inclusion, and a workplace catalysed by forward thinking and future-proofing. Today, it brings together over 16,000 talented professionals across eight countries in the Middle East, with a presence in LATAM. Their collective efforts have earned the Group the Great Place to Work® certification in several markets. Sustainability is at the core of the Group’s strategy, guided by a clear commitment to people, partners, and the planet. Chalhoub Group is proud to be a member of the United Nations Global Compact, a signatory of the Women’s Empowerment Principles, and to have pledged to reach Net Zero by 2040. What You'll Be Doing We are looking for a Senior Data Scientist to design, build, and continuously improve machine learning models that enable predictive and intelligent decision-making across business functions, ensuring accuracy, fairness, and robustness through rigorous experimentation, tuning, and monitoring. Key Accountabilities 1. Design and develop machine learning models for predictive, classification, or optimization use cases aligned to business needs. 2. Own model training, tuning, and evaluation, using appropriate techniques to optimize performance, precision, and recall. 3. Engineer and select relevant features, leveraging statistical and domain knowledge to improve model outcomes. 4. Implement experiment tracking frameworks to ensure reproducibility and model comparability across versions. 5. Establish and maintain model performance metrics, including accuracy, F1 score, AUC, etc., depending on use case. 6. Develop strategies for detecting model drift, including statistical monitoring of input data and prediction shifts. 7. Define retraining strategies and triggers based on performance degradation, data shifts, or periodic review cycles, in collaboration with MLOps and platform teams. 8. Ensure fairness and mitigate model bias, applying techniques to identify and reduce demographic or systemic disparities. 9. Collaborate with Data Engineers, MLOps, and Product Managers to integrate models into production pipelines. 10. Document and version all models, experiments, and assumptions to support auditability, governance, and reuse. 11. Apply generative AI techniques, including LLM fine-tuning, embeddings, and retrieval-augmented generation, to support NLP and conversational use cases. 12. Link model outputs to Success KPIs by quantifying value creation (e.g., time saved, accuracy improvements, or revenue impact). What You’ll Need To Succeed • 5–7 years of experience in applied data science or machine learning. • Strong proficiency in Python, machine learning libraries (e.g., scikit-learn, XGBoost, LightGBM), and experimentation tools (e.g., MLflow, Weights & Biases). • Solid understanding of model development lifecycle: training, hyperparameter tuning, evaluation, deployment, monitoring. • Proven experience in feature engineering, including categorical encoding, normalization, and feature importance analysis. • Knowledge of model performance metrics, statistical validation, and A/B testing approaches. • Familiarity with bias detection techniques and fairness frameworks. • Experience with drift detection methods (e.g., population stability index, data drift metrics) and retraining triggers. • Comfort working with structured and semi-structured data, including tabular and time-series formats. • Strong collaboration skills; able to work with MLOps, engineering, and product teams in cross-functional environments. • Working knowledge of MLOps practices (e.g., containerization, CI/CD, model serving) to ensure models are production-ready and scalable. • Hands-on experience with Azure ML and GCP Vertex AI for model training, deployment, and monitoring. What We Can Offer You With us, you will turn your aspirations into reality. We will help shape your journey through enriching experiences, learning and development

5–7 years of experience in applied data science or machine learning. Strong proficiency in Python, machine learning libraries (e.g., scikit-learn, XGBoost, LightGBM), and experimentation tools (e.g., MLflow, Weights & Biases). Solid understanding of model development lifecycle: training, hyperparameter tuning, evaluation, deployment, monitoring. Proven experience in feature engineering, including categorical encoding, normalization, and feature importance analysis. Knowledge of model performance metrics, statistical validation, and A/B testing approaches. Familiarity with bias detection techniques and fairness frameworks. Experience with drift detection methods (e.g., population stability index, data drift metrics) and retraining triggers. Comfort working with structured and semi-structured data, including tabular and time-series formats. Strong collaboration skills; able to work with MLOps, engineering, and product teams in cross-functional environments. Working knowledge of MLOps practices (e.g., containerization, CI/CD, model serving) to ensure models are production-ready and scalable. Hands-on experience with Azure ML and GCP Vertex AI for model training, deployment, and monitoring.

Design and develop machine learning models for predictive, classification, or optimization use cases aligned to business needs. Own model training, tuning, and evaluation, using appropriate techniques to optimize performance, precision, and recall. Engineer and select relevant features, leveraging statistical and domain knowledge to improve model outcomes. Implement experiment tracking frameworks to ensure reproducibility and model comparability across versions. Establish and maintain model performance metrics, including accuracy, F1 score, AUC, etc., depending on use case. Develop strategies for detecting model drift, including statistical monitoring of input data and prediction shifts. Define retraining strategies and triggers based on performance degradation, data shifts, or periodic review cycles, in collaboration with MLOps and platform teams. Ensure fairness and mitigate model bias, applying techniques to identify and reduce demographic or systemic disparities. Collaborate with Data Engineers, MLOps, and Product Managers to integrate models into production pipelines. Document and version all models, experiments, and assumptions to support auditability, governance, and reuse. Apply generative AI techniques, including LLM fine-tuning, embeddings, and retrieval-augmented generation, to support NLP and conversational use cases. Link model outputs to Success KPIs by quantifying value creation (e.g., time saved, accuracy improvements, or revenue impact).