Principal Data Scientist

JOB DESCRIPTION 

Key Responsibilities: 

• Develop, maintain, and optimize forecasting Machine Learning (ML) models for better accuracy. Collaborate with other data scientists and data engineers to ensure that specifications are translated into flexible, scalable, and maintainable solutions. • 
• Research and stay abreast of state-of-the-art machine learning technologies. • Follow code standards and best practices. 
• 7-8 years experience in data science or 3 years direct experience building forecasting solution. Familiar with forecasting algorithms, such as Time Series (Arima, Prophet), ML (GLM, XgBoost), Hierarchical model (Top Down, Bottom Up), DL (Seq2Seq, Transformer), and Ensemble methods. • 
• Hands-on experience with building end-to-end ML models and pipelines. • Experience with Git, Bitbucket, Airflow, MLflow, Kubeflow, GCP Vertex AI, Databricks or equivalents. 
• Experience & Knowledge of large-scale data processing and distributed systems such as Hadoop and SPARK. • Strong coding skills in Python, Spark and SQL. 
• Strong communication and collaboration skills • Exposure in various statistical modelling, machine learning algorithm/techniques (ML) Experience with optimisations, debugging, fine-tuning existing applications in distributed computing environment for high performance and scalability with Big Data. •
• Experience with an agile development environment. • Exposure in tools/framework to monitor and analyse ML model performance and data accuracy. 
EXPERTISE AND QUALIFICATIONS Technical Skills: 
• Time series
• SQL
• Python 
• Experience in working with large
volume data and Pyspark environment as mandatory