Data Scientist

We are looking for two hands-on Senior Data Scientists to design, build, and productionize an advanced recommendation engine on Azure Databricks. The role requires strong expertise in deep learning, recommender systems, embeddings, and production-grade ML.

Responsibilities:

• Design and build recommendation models for retention, cross-sell, next-best-action, and quantity prediction.
• Develop advanced deep learning recommenders using neural collaborative filtering, two-tower architectures, deep embeddings, sequence-based models, and transformer-based approaches.
• Build customer, product, and interaction embeddings for personalised recommendations and ranking.
• Develop scalable feature engineering, training, evaluation, and inference pipelines on Azure Databricks.
• Design robust evaluation approaches including temporal validation, ranking metrics, explainability, and A/B testing.
• Productionize models with MLflow, automated retraining, model monitoring, drift detection, and CI/CD.
• Independently own the data science lifecycle from problem formulation through production deployment and continuous improvement.

Requirements:

• 5+ years of hands-on experience in Data Science and Machine Learning, including production-grade ML solutions.
• Advanced degree such as M. Tech, MS, MSc, or PhD in Computer Science, Computing, Mathematics, Statistics, or a related quantitative discipline.
• Academic background from a Tier 1 or Tier 2 engineering, science, or technology institution.
• Strong expertise in deep learning and modern recommender-system architectures.
• Strong hands-on experience with Python, PySpark, SQL, PyTorch or TensorFlow, Azure Databricks, and MLflow.
• Strong understanding of embeddings, ranking, personalisation, model evaluation, explainability, MLOps, and production deployment.
• Ability to independently architect and build complex ML solutions and work effectively with engineering and business teams.

Good to Have:

• Hands-on experience with Generative AI, LLMs, RAG, and embedding-based retrieval.
• Exposure to Agentic AI, including multi-agent systems, tool-using agents, and agentic workflows.
• Experience integrating GenAI or Agentic AI capabilities with traditional ML and recommendation systems.