Implemented end to end solution for Creation of a unified 360 view of the customer by moving data from source system (Salesforce, CRM, Google Analytics, Google Ads, Google Ad manager, Facebook and POS) with BigQuery Data Transfer Service (DTS) and third-party transfers to Google Customer Data Platform (CDP).Leveraging Vector Databases for Next-Level E-Commerce Personalization. Implementing personalized product recommendations (Collaborative Filtering, Content based and Demographics Based )to improve user experiences.Leverage Vertex AI, Tensorflow and Keras for Model evaluation for ensuring that ML systems deliver reliable, accurate, and high-performing results in productionData quantization is used to compress data points to save space and reduce indexing time.Develop and maintain automated processes for deploying machine learning models into production while ensuring adherence to governance policies related to quality, monitoring, and compliance.Implement and manage CI/CD pipelines for ML workflows to ensure seamless integration, delivery, and compliance with governance standards.Monitor model performance in production, ensuring models comply with governance policies and ethical standards.Break Down the Product into Themes and Epics and Prioritize Features Based on ValueEstablish a Dynamic Release Plan with Release Planning, Incremental Delivery and VersioningUse retrospectives to evaluate if the current roadmap aligns with the team's velocity and capacity.Constantly gather user feedback on delivered features to refine future roadmap items and re-prioritize.Visualize the Agile Product Roadmap using Kanban Board and Gantt Chart

 Design the Digital Research Environment that provide a mechanism to ingest, curate, integrate and manage the diverse data relevant for drug discovery activities. Platform produced a ranked list of potential ALS, treatments, together with biological evidence. The ML team was able to rapidly triage these predictions using strategies focused on pathways implicated in multiple ALS processes. Client aims to use the power of AI to put patients first, and tangibly transform their lives by creating a way to lower drug discovery and development costs, decrease failure rates and increase the speed at which medicines are delivered to patients.

 Leading product development team for a DI&A a powerful & secure B2B ETL and analytical platform for Client using Rest API, KAFKA, Blob , Synapse, Spark Structured Streaming with Kappa Architecture Hosted on Azure Databricks. Implemented CI/CD with Design , Build, Release and Deploy using Azure Devops Monitoring data processes and quality and access controls and security built-in at every stage using Collibra Implemented continuous ingestion of data from various sources using Delta Live table, Kafka and Unity Catalog. Develop Testing Roadmap for Data Integration Solution. (Data Accuracy, consistency, Security in Transit, Compliance Testing.) Lead the development and training of large language models (LLMs) for various applications . Utilize the LangChain and RAG frameworks to build robust AI-driven solutions. Design and implement evaluation metrics to assess model performance and improve algorithms using Tensorflow.

Lead the Enterprise Data Architecture team with overall end to end accountability for technology strategy, design, deliveryand operation for all of our global internal systems.Design and Develop architectures using Azure Data platform capabilities like Azure Data Lake,Azure Data Factory,Azure SQL, Azure SQLDW, Azure SQL Managed Instances for data ingestion and data transformation capabilities.Design Multi-channel campaign Management by providing access to the In-scope Data Source for creating Interaction.Git, Pull Requests, Branch Policies, and implement Continuous Integration using Azure DevOps and Source Control with Git

 Design and implement Enterprise DataWarehouse with Operational Data Store that semiautomatically extracts information collected in Health Level 7 Clinical Document Architecture (CDA) documents stored in an EHR and transforms them to be loaded in a target data warehouse. OnLine Analytical Processing (OLAP) tables were created to accommodate team analysis. The data source layer is set of legacy systems and repositories (Electronic health care record, laboratory information systems, radiology information systems) File Format: Relational databases, XML, flat/binary files, and spreadsheets Design middleware system, called operational data store (ODS), contains detailed and integrated data with specific constraints including referential integrity that ensures data accessibility by relevant units. Identify the Fact Dimensional model can be chosen among the Act classes of the CDA depending on the data to be collected and the analysis to be done. Identify the Dimensions from the Act chosen and a Fact of the dimensional model, the CDA document is navigated in both parent–child and child–parent direction to include the relevant Act classes and HL7 Hierarchies to the data warehouse dimensional model