Summary:

• I have dynamic 13+ years’ experience as a Data Scientist/Data Analyst with a master’s in business Intelligence and deep experience analyzing commercial data using reporting tools like Tableau, Python, SAS, and SQL across Fintech companies.
• Well-versed in deriving viable solutions to complex business problems through big data analysis and management.
• Solid understanding of Power BI desktop, Power Query, and DAX formulas.
• Proficient in containerization and orchestration using Docker and Kubernetes for scalable deployment of ML applications.
• Implemented comprehensive monitoring and logging using Prometheus, Grafana, ELK Stack, and Azure Monitor to ensure model and infrastructure health.
• Designed and implemented MLOps solutions on AWS, GCP, and Azure, leveraging cloud-native services for scalable and resilient deployments.
• Utilized tools such as Apache Airflow, Luigi, and Kubeflow Pipelines to automate end-to-end ML workflows, from data ingestion to model deployment.
• Developed comprehensive monitoring and alerting systems using tools like Prometheus, Grafana, and CloudWatch to ensure high availability and performance.
• Implemented automated model drift detection systems to monitor and alert model performance degradation over time.
• Collaborative work with cross-functional teams and utilization of diverse technologies (Python, Scala, TensorFlow, PyTorch).
• Utilized python’s flask framework for building REST APIs on top of Data Lake (BigQuery, Cloud SQL).
• Achieved Continuous Integration &Continuous Deployment (CI/CD) for applications using Git, Azure Devops.
• Experience with Test driven development (TDD), Agile methodologies and SCRUM processes.
• Hands on solving problems which brings significant business value by building predictive & forcasting models utilizing structured & unstructured data.
• Extensive experience managing and engaging stakeholders at all levels including communicating technical concepts to non-technical audiences.

Areas of Expertise include:

Data Analysis | Data Science | SQL | Tableau | Data Visualization | Python | Stakeholder Engagement Agile Scrum Master | Agile Product Owner | Lean | CI/CD | TDD | Gap Analysis | Process Mapping Data Modelling | Process Improvement | Problem-solving | Communication & Influencing

EDUCATION

• Master’s. Information Technology Management | University of Texas, Dallas, USA 2015
• B.Tech. Information Technology | Narsee Monjee Institute of Management Studies, Mumbai, India 2010

PROFESSIONAL EXPERIENCE: –

Intuit (Mountain View)

Sr Data Scientist/Business Data Analyst 4                                                                                                        Aug 23 – Present

• I worked on multiple analytics projects like cohort analysis, GNS analysis, and mobile analysis for the QBLive team.
• Maintain and update the Intuit Assist (IAQB) Tableau dashboard.
• I ran the OIPRO A/B test experiment from scratch and built a Tableau dashboard to view the performance and present insights in the WinRoom Experiment review.
• Developed automated workflows for model retraining and deployment based on data drift and performance metrics using Apache Airflow and Kubeflow Pipelines.
• Integrated LLM-powered chatbots into eBay's messaging system to provide real-time responses to customer queries, improving response times and user satisfaction.
• Designed and implemented robust machine learning pipelines using Kubernetes(K8)/AKS with Argo Workflow orchestration, ensuring scalable and efficient end-to-end ML processes.
• Managed data pipelines for ML workflows on Kubernetes(K8)/AKS using Argo Workflows, ensuring efficient data movement and transformation between pipeline stages.
• Built and maintained end-to-end machine learning pipelines, from data ingestion to model deployment, using tools like Apache Airflow, MLflow, and Kubeflow.
• Designed and implemented CI/CD pipelines for machine learning models using Jenkins, GitLab CI, and Azure DevOps, ensuring rapid and reliable model deployment.
• Containerized machine learning applications using Docker and deployed them on Kubernetes clusters, ensuring high availability and scalability.
• Implemented monitoring and logging solutions using Prometheus, Grafana, ELK Stack, and Azure Monitor to track model performance and infrastructure health.
• Utilized MLflow and DVC for model versioning, tracking, and reproducibility, ensuring consistent and reliable model deployments.
• Developed Spark code using Scala and Spark-SQL for faster processing and testing, integrating MLOps practices for efficient development workflows.
• Performed data cleaning and feature selection using MLlib package in PySpark, working with deep learning frameworks such as Caffe with considerations for MLOps.
• Integrated CI/CD pipelines with Argo Workflows and AKS to automate the deployment of updated machine learning models, ensuring continuous delivery and integration.
• Created an algorithm that can predict the type of the object in a typical house using Deep Learning. Used OpenCV for the image analysis and keras and Tensorflow for implementing artificial neural networks (ANN).
• Developed doctor report cards for real-time insights into their performance over the years. Using Apache Kafka for data ingestion and Tableau integrated with Hadoop/Spark for creating the reports.
• Create a self-serve tool to view DIWM trailers performance and automate all the processes.
• Make a lot of enhancements to the GSU SOT dashboard.

Apple (Sunnyvale)                                                                                                         Jun 21 – Aug 23

Senior Data Analyst

• Implement BERT NER NLP model on Apple Care raw unstructured data to identify personal health information of customers and redact it.
• Create API also to find PHI and customer passwords from raw customer data.

Achievements/Tasks

• Collaborated with data engineers and operation team to implement ETL process, wrote and optimized SQL queries to perform data extraction to fit the analytical requirements.
• Built NLP models including BERT, and XGBoost to find personal health information.
• Performed univariate and multivariate analysis on the data to identify any underlying pattern in the data and associations between the variables.
• Performed data imputation using Scikit-learn package in Python.
• Analyzed customer data and market trends to identify new growth opportunities.
• Utilized data visualization tools and statistical analysis to create comprehensive reports and presentations, providing valuable insights to the executive team and supporting data-driven decision-making.
• Participated in features engineering’s such as feature intersection generating, feature normalization and label encoding with Scikit-learn pre-processing.
• Used Python 3.X (NumPy, SciPy, pandas, scikit-learn, seaborn) to develop various models and algorithms for analytic purposes.
• Created and managing reports, dashboards, and visualizations using Tableau.
• Built multiple Splunk dashboards for API usage and set up usage notifications on slack and email using slack webhooks.

GSK (India)                                                                                                         Oct 20 – Jun 21

Data Analytics Manager

• Owned and manage algorithm team at GSK. Implement Next Best Action project to 30 countries to drive pharma growth.

Achievements/Tasks

• Optimize the current algorithm use case to provide better recommendation to achieve 1.5% growth in revenue overall.
• Implement NBA project to 30 new global markets.