Satish Bhambri

Personalization, Ranking, Generative AI Architect and lead development of enterprise-scale AI systems supporting personalization, ranking, and discovery at massive scale. Designed and deployed multimodal image similarity and product variant intelligence pipelines, integrating vision language embeddings, large-scale vector retrieval, and business-aware ranking logic to power product discovery and relevance. Led development of agentic RAG systems for enterprise reporting and decision support, enabling AI-driven retrieval, reasoning, and workflow orchestration over structured and unstructured data. Collaborated cross functionally across engineering, product, and infrastructure teams to operationalize AI systems under strict latency, reliability, and governance constraints.

• Designed and Developed GroceryBot using transformer embeddings, GCP and VertexAI Matching Engine for ANN vector similarity search, Implemented grounded and Retreival Augmented Generation LLM(text-bison). • Developed NLP models for Smart Ads Recommendation using Topic modelling and transformers like KNN, BERTopic, Topic2Vec and Two Towers resulting in an increase in click-through rates. • Developed Evaluation metrics for smart ads without customer feedback ground truth using cosine similarity, KeyBERT MMR, Longformers. (Supervised proxy problem and Smoke Tests for unsupervised learning) achieving a 15% improvement in personalized recommendations. • Led experiments to enhance Diversity metrics for recommendations, increasing the potential diversity score by 25%. • Optimized recommendation generation using CuML, RAPIDS, and NVIDIA GPUs, reducing processing time. • Developed Recipe Recommendations with KNN, Content Based and Collaborative filtering, LLMs and Generative AI goes well with section.

The place where entrepreneurs, innovators and investors come together to share ideas and shape our future. Ground zero in Silicon Valley for new technologies and ventures. Lets collaborate and build future together !

- Developed Risk As A Service, identifying the supply chain disruption hotspots for Natural Disasters and Impacted ports and freight using Azure functions, Java, NLP, Naïve Bayes, Random Forests and LightGBM, leading to potential $2 million in cost savings. - Engineered data pipelines for predicting shipment time of arrival, reducing prediction errors by 40%, using microservices, Kafka, Data Lake, Synapse Db, Apache Ignite Cache, and ML models of NLP and Tree based ensemble methods, Bayesian Heuristics. - Dockerized Java applications and orchestrated deployments on Azure using DevTest Labs and MULE, resulting in a 20% reduction in deployment time. - Developed Automated Integration Estimate Recommendor streamlining customer pitch preparation and increasing customer engagement by 14%. - Developing Optimized Warehouse Management solutions using Statistical Machine Learning. - Developed Azure DevTest Labs On-the-go provisioning environments for Development and Testing. - Designed, Developed and Dockerized the Applications and productize containers on Azure and Azure Container Registery - Development of Jenkins jobs for setting up of maven SNAPSHOT and Release repositories with JFrog. - Developed Framework components using Mule ESB, JAVA and XML SDK’s and developed adapters for integration between JDA Applications.

Developed Integration Platforms using Java, Mulesoft and APIs. Developed custom connectors using Java, XML, Mule SDKs. Dockerizing the Deployment, Setting up entire production deployment pipeline using Dockers, Mule, Jenkins and Automating the Server registration on the Multi-cloud platforms using Azure and Azure Container Registry.

Developed Point of Sale systems using Java EE, Hibernate, and Service oriented Architecture. Developed the modules for the efficient management of QR codes on the point of sale systems. Alexa skills for EOD reports and analysis.

- Implement and maintain build system deploying object oriented design, production Python Code, continuous Integration for chip simulation. - Develop Linux Kernel modules and Common Clock framework drivers.

- Awarded SUN award for Continuous Improvement, Customer Satisfaction and Excellent Performance. - Backend management of Blackboard and content management - Technical Simulations using Python, Bokeh and Flask - Worked in the domain of Data collection, Data Pre-processing, statistical analysis and data visualization such as modelling of data for instance non-linear relationships using polynomial feature selection, Random forest Regressors and non-linear data transformation, and text analysis, Scikit-learn libraries such as cross validation, Standard scalar for data splitting, Dimensionality reduction using Principal Component Analysis and Pipelining the data for application of suitable machine learning algorithm. - Developed models using Regression analysis, forecasting, feature selection, and model performance analysis using parameters such as confusion matrix, classification reports, scatterplots, precision scores, recall scores, f1 scores, MSE and RMSE, R2 scores and parameter optimization such as while constructing an estimator using Grid search hyper parameter fine tuning for estimator. - Experienced at addressing the problems of overfitting of models using regularization, Ridge Regression, Least Absolute Shrinkage and Selection Operator (LASSO), and Elastic Net Regression methods.

- Developed service oriented, client-server, web/Desktop based distributed enterprise applications using Java and Microsoft technologies of C#. NET, ASP.NET, ASP.NET MVC, WPF, and WCF. - Worked with Java Spring, Hibernate, Maven and JUnit and .NET security features such as Authentication & Authorization, Windows and Forms Authentication, and Active Directory and XML Web Services, designing WCF the front end using XAML Browser based WPF and Silverlight for rich UI. Consumed Web Services from both Windows forms and ASP.NET web apps. - Developed applications with XML technologies including XML, XSLT, XSD, XML Schemes, and SOAP, REST, JSON and AJAX, Java EE, JAX-WS, JAXB, RDBMS Architecture, Model, Design & Development including SQL Server, T-SQL, Oracle, SQL, PL/SQL. American Multinational Energy Corporation Client - Configured Solarc Right Angle(PB & .NET), deployed ETRM business rules. - Worked with Production team migrating and deploying on Breakfix, Staging and Production environment, and Version Control using TFS. AESO (Alberta Electric System Operator) Client - Customized SharePoint and hosted WCF services and Deployed Service Registry(UDDI) Model, SOAP and REST APIs. - Configured DMZ zone for Security Model POC’s and Implemented Active Directory Authentication(Forms based). Junior Associate Tech, Sapient GM. (January, 2015 – July, 2015) - Developed applications leveraging ADO.NET, LINQ to SQL, Entity Framework 4/ 4.5, DOM and SAX Parsers for XML services. - Developed an Equity Trading Application : Automated Equity trade, accounts and reporting. Implemented WCF Data Services using Service Agility and scalability and Deployed LINQ to SQL for object relational mapping to model relational database. - Deployed Entity Data Model, building N-tier solution using entity framework, WPF and Code first approach. Deployed Websites, having 3-tier architecture (Web Server, Web Services server, Database server).

Have pursued the courses of - Statistical Machine Learning, Semantic Web, Applied Project 1, Distributed Software Development (A), Quantum Information Processing (A), Advanced Data Structures and Algorithms (A), Software Enterprise - Inception and Elaboration(B), Microcomputer Architecture (A+), Software Enterprise - Process and Project Management (data-driven software solutions and business decision making) (A-), Operating Systems and Networks(B+), Languages and Programming Paradigms(A-) - Applied Project : Developing a web and desktop based PLP and MIPS tool using Java Spring, Maven and Hibernate for the microprocessor simulations for students not having access to actual microprocessor labs Online Courses : - Machine Learning (Stanford Coursera), Data Mining, Statistics for Data Science and Analytics(Stanford Online), Data Science Specialization and Capstone (Coursera), Data Visualization

- Winner, Equities Trading Simulation @ Sapient Global Markets. - Project Manager for the Mock Project, created Master Data Management Solution (MDMS). - Research published : https://ui.adsabs.harvard.edu/abs/2014arXiv1410.6502B/abstract