About Grofers
Grofers is revolutionising e-commerce by making essential items available to customers in under 10 minutes. We leverage technology, data sciences, and rich customer insight, resulting in a dense and fast network of dark stores. Our ambition is to grow 100x in the next five years, becoming one of the most important e-retail companies in India. We are looking for ambitious, smart builders who take extreme ownership and commit to making outcomes happen.
About the Data Science team
The Grofers Data Science team tackles a multitude of challenges across end-to-end operations, including Product recommendations, Demand Forecasting, MarTech, Customer-segmentation, Automated Vehicle-routing, and Inventory-replenishment optimisation. We operate in a fast-paced environment with high autonomy and ownership, focusing on business impact. If you enjoy learning end-to-end and are committed to getting things done, you'll thrive in our talented and spirited team.
What you will do
- Collaborate with various stakeholders to identify complex business problems and translate them into data-driven solutions.
- Solve a wide range of Location-intelligence based sub-problems impacting different parts of the Grofers demand and supply systems.
- Lead brainstorming sessions with the team at the start of projects.
- Prioritise problems in the Grofers’ supply chain to decrease cost and increase efficiency, or work on the demand side to increase revenue and conversion.
- Perform Exploratory data analysis for large datasets.
- Publish work in peer-reviewed journals and represent Grofers at conferences.
- Handle a team of junior Data Scientists.
- Lead Data Science project teams and be responsible for overall deliveries and code quality from the Data Science side.
What you need
- B.Tech / Masters / PhD degree in Computer Science / Statistics / Mathematics / Economics or related quantitative field.
- Minimum 6 to 8 years of relevant experience (6 years in case of PhD) in areas like Geospatial analysis, Regionalisation and Clustering algorithms, Data Enrichment, Machine Learning.
- Strong foundations in mathematical aspects including Linear Algebra, Probability Theory, Statistical Modeling, Analysis of Variance, Convex Optimization, Hypothesis Testing, Data Structures, Multivariate Calculus.
- Hands-on experience with supervised machine learning methods like Decision Trees, Random Forests, Support Vector Machines, Neural Networks, Time Series.
- Knowledge of unsupervised and feature engineering machine learning methods like Principal Component Analysis, Clustering, Word2Vec, One-Hot-Encoding.
- Work experience in at least one Data Science Language (Python / R / MATLAB / Octave).
- Strong understanding of the Python ecosystem around GIS capabilities.
- Strong understanding of public datasets available around the GIS domain like OSM, OSRM, Gridding libraries, Raster formats, CRS systems.
- Proficiency in Database System Concepts and working knowledge of PostGIS or any other SQL on GIS.
- Strong understanding of all stages of taking a Model to production, including feature scouting, data wrangling and cleaning, feature engineering, algorithm selection, validation techniques, working with large datasets, rolling out versioned Models in production using A/B Test, and measuring KPIs in production.
- Experience with big data tools like Spark, Hadoop is a plus.
- Domain knowledge in Supply Chain / BlockChain and concepts like Queuing Theory, Inventory Management, Warehouse Layout Design, Forecasting Techniques, Genetic Algorithms, Game Theory, Simulated Annealing is a plus.