Sr. Data Scientist

Job Summary:

The primary purpose of this role is to focus on developing and deploying advanced statistical models and machine learning techniques to accurately predict future trends, behaviours, and outcomes based on historical data. This position combines deep expertise in data science with a specialized focus on time series analysis, demand forecasting and predictive analytics to support business decision-making, optimize operations, and drive planning.

Roles & Responsibilities:

• Develop, maintain, and optimize forecasting Machine Learning (ML) models for better accuracy.
• With focus on AI/ML techniques, build and deploy state of the art predictive models for use cases like item location level demand forecast, inventory and capacity planning, network flows, labour scheduling & supply chain optimization
• Responsible for extracting actionable insights from large and complex datasets, developing predictive models, and guiding the organization in using data to improve products, services, and operations
• Collaborate with analysts, data engineers, product managers, other data scientist & leadership to translate business requirements into actionable data science solutions.
• Championing best practices and consistently working to enhance our production pipelines to improve reliability, scalability, and efficiency in terms of both time and memory.
• Research and stay abreast of state-of-the-art machine learning technologies.

Years of Experience:

• 5-8 years' experience in Data science.

Required Minimum Qualifications:

• Bachelor's/Master's degree in engineering, Computer Science, CIS, or related field (or equivalent work experience in a related field)

Skill Set Required

• Familiar with forecasting algorithms, such as Time Series (Arima, Prophet), ML (GLM, GBDT, XgBoost), Hierarchical model (Top Down, Bottom Up), DL (Seq2Seq, Transformer), and Ensemble methods.
• Hand-on experience (real-time) in building end-to-end ML models and pipelines.
• SQL, Python, Spark, Py Spark.
• Big Data systems - Hadoop Ecosystem (HDFS, Hive, MapReduce) or Cloud
• MLflow, Kubeflow, GCP Vertex AI, Databricks or equivalents.
• Analytics database like Druid, Data visualization/exploration tools like Superset.
• CI\CD · GIT

Secondary Skills (desired)

• Apache Airflow, Apache Oozie, Nifi
• GCP cloud experience, Big Query, GCP Big Data Ecosystem.
• Trino/Presto
• Domain experience on retail forecasting or any other business forecast predictions/time series forecasting

Job Type: Full-time

Pay: ₹3,000,000.00 - ₹4,000,000.00 per year

Benefits:

• Health insurance
• Provident Fund

Work Location: In person