Senior Full-stack Data Scientist

About the RoleWe are looking for a Full-Stack Data Scientist to join our central analytics & ML team. In this role, you will own end-to-end development of machine learning solutions — from problem discovery, data exploration, feature engineering, model development, deployment, to post-production monitoring.You will work on high-impact domains across Masan’s retail, FMCG, supply chain, and customer ecosystem, dealing with large-scale, multi-channel data.Key ResponsibilitiesTranslate business problems into analytical/ML solutions with clear measurable impact.Perform EDA, build hypotheses, and validate insights using large-scale structured & unstructured data.Build, tune, and evaluate ML models (classification, forecasting, optimization, segmentation).Develop production-ready features and contribute to the Feature Store.Work on big data environments (Spark, PySpark, Databricks, Delta Lake).Ensure data quality, lineage, and consistency across pipelines.Package and deploy ML models using MLflow, FastAPI, Docker, and CI/CD workflows.Collaborate with Data/ML Engineers to operationalize models at scale.Set up monitoring dashboards: model performance, drift detection, data quality, retraining triggers.Continuously track model performance and business KPIs after deployment.Optimize and retrain models based on real-world feedback.Communicate findings, insights, and recommendations to business teams in a clear and actionable way.Explore new techniques (LLMs, embeddings, RAG) when relevant to business problems.Prototype solutions rapidly and iterate based on feedback.QualificationsFor Middle-level candidates2+ years of hands-on experience in applied machine learning.Strong Python skills (pandas, sklearn; PySpark is a plus).Solid understanding of statistics, algorithms, data structures.Experience building and validating production-ready ML models.For Senior-level candidates4+ years of end-to-end ML experience solving real business problems.Proven track record of deploying, monitoring, and optimizing ML models in production.Experience leading projects and partnering with cross-functional stakeholders.Both levelsExperience with MLflow, FastAPI, Docker, or similar deployment tools.Experience with cloud or big-data environments (Azure, Databricks, Spark/Delta).Strong communication and ability to explain technical topics to non-technical teams.Product-oriented mindset with strong ownership and a bias for impact.Nice to haveHands-on with LangChain, OpenAI API, prompt engineering.Kaggle competitions, research publications, or AI side projects.Key note: We understand that year-end can be a sensitive time for career transitions; therefore, we are open to negotiating the start date to best suit your situation.