About the opportunity:
As a Lead Data Scientist on the Demand Forecasting team, you will develop models and algorithms to predict the incoming demand for FMCG firms. You will closely work with the demand planning and backend teams to continuously learn more about our business and to particularly develop an understanding of the various processes we have in play. You will partner with ML Engineers and Applied Scientists to build solutions including development, deployment, and maintenance of algorithms and models at scale.
Your responsibilities
- Build upon the incumbent demand forecasting processes and practices
- Develop novel models to further improve our demand sensing accuracy
- Work with the MLOps and back-end teams to develop and streamline pipelines
- Help automate various phases of the model development: ETL, EDA/pre-processing, feature engineering, model selection/optimisation, and deployment.
- Collaborate with the Operations Research team to effectively integrate the forecasts with our optimisation models
Basic Qualifications
- B.Sc/M.Sc in Mathematics, Statistics, Operations Research, Computer Science, or in a related Mathematical or Computational Engineering major
- 3+ years of experience in building forecasting models, artificial intelligence models, optimisation algorithms or equivalent school experience
- Proficient in one or more of R, Python, C++, Java, Scala or equivalent programming language
- Strong domain knowledge within the Inventory Management and Time Series spheres
- Knowledge of linear algebra, statistics, information theory or related mathematical domains
- Understanding of deep learning, dynamic programming, or related areas
- Ability to test and measure algorithms
- Excellent written and verbal communication skills
Preferred Qualifications
- PhD in Data Science/Computer Science or a related field
- Experience with microservices architecture components, including Docker and Kubernetes
- Experience developing microservices to fit data cleansing, transformation and enrichment needs
- Experience with Jira, Confluence and extensive experience with Agile methodologies
- Experience in developing flexible data ingest and enrichment pipelines to easily accommodate- new and existing data sources
- Experience with continuous integration and deployment (CI/CD) pipelines and their enabling tools such as Jenkins, Nexus, etc
- Detailed oriented/self-motivated with the ability to learn and deploy new technology quickly