Currently contributing to AI projects, focused on developing and optimizing machine learning and deep learning algorithms to predict diverse outcomes. Utilizing cloud technologies such as Azure ML Studio, Azure Functions, Azure Event Hub, and Azure Streaming Analytics, that efficiently gather input, interpret features, and deliver results to frontend applications.

List of the projects, tools, and technologies I have worked on:* Utilized Natural Language Processing (NLP) techniques to build predictive classification models, integrated into OpenWells® Plugin as a Rest API for text description columns.* Implemented reservoir engineering applications employing RNN and UNET architectures (keras, TensorFlow, pyTorch) to predict time series data like pressure, oil, gas and water saturation from dynamic/static datasets.* Developed and integrated ML and statistical algorithms (scikit-learn, TensorFlow, pyTorch) on AWS cloud.* Deployed, integrated, and maintained JupyterHub/Z2JH (statistical analysis and visualization) with the reservoir engineering application on cloud platforms using Dockers, Kubernetes, and Helm charts.* Collaborated closely with geo scientists and drilling engineers, applying algorithms to datasets and deploying them on cloud.* Currently working on Restplus framework to build rest APIs for reservoir management, saving application data to MongoDB (NoSQL), PVC, and Azure blob.* Utilized machine learning approaches to identify patterns in oil and gas datasets for optimization tasks, such as history matching.* Utilized Terraform (Infrastructure as Code) for cloud services management.* Deployed Restful services on servers with high-performance connection handling mechanisms, using Nginx and Gunicorn.* Provided unit test cases and documentation for APIs responses.* Created and visualised data using Python libraries like Matplotlib, Seaborn, and Plotly.* Utilized TIBCO Spotfire for oil and gas data analysis charts.* Implemented Python-based PDF to Excel parsing using various libraries.* Utilized Python-based text extraction from images (OCR).

I have actively engaged in projects, tools, and technologies related to machine learning, streaming applications, and software development which are mentioned below: 1- Human depression detection from voice data (patient audios) using python deployed as a Rest API (python flask). Model uses machine learning and deep Learning (CNN) techniques to classify human depression scale. Dataset comprises of US patients voice recordings (EULA signed dataset) 2- Utilised multi-labeled classification techniques in Python, I developed a machine learning-based Rest API (Flask) with a web interface for HR, Admin, and higher management. The system predicts employee store items and performs data analysis using a comprehensive dataset spanning 11+ years of MTBC employee records.3- AI chatbot implementation on rasa core and rasa NLP deployed on private linux server. 4- MTBC symptom checker react native (android and iOS) based application (SQL for DB) that uses machine learning based rest services to evaluate patient’s symptoms, ICD/CPT prediction and summary generation. 5- Optimised symptom checker service that utilised machine learning algorithms and ensemble techniques in collaboration with domain experts. 6- Developed and integrated telemedicine (video calling, text chatting, screenshot etc.) featured product using WebRTC, NodeJS, Javascript, SQL and Rest API. Product URL: http://www.talkehr.com 7- NodeJS based standalone APIs of Telemedicine on docker container, saving session IDs in Mongo DB and Swagger (NodeJS) dashboard of APIs documentation. 8- Real-time messages transfer in .NET based TalkEHR product using SignalR.

Actively involved in the development of two notable applications. The first project, LiveShops, focused on creating a cutting-edge live stream cordova hybrid app (android and iOS platforms). Leveraging a stack of advanced technologies such as WebRTC, Ruby on Rails, NodeJS, Ionic, AngularJS, SQL, JS, and real-time server-side technologies. Additionally, I played a key role in deploying the streaming application on the AWS cloud, utilizing EC2, S3, and RDS for optimal performance. In the second application, I contributed to the development of an online meeting web application tailored to the specific needs of a private company. The application incorporated features like video and audio conferencing, text chat, broadcasting, screen sharing, and more, with the support of technologies such as WebRTC, NodeJS, Java, JS, and various server-side technologies.

Experienced in developing dynamic and user-friendly web applications using an array of technologies including JavaScript, Python, CodeIgniter, PHP, AngularJS, CSS, JavaScript, and WordPress, to create seamless digital experiences for diverse audiences.

Worked on a project Indigenous Automation System (PVT) LTD.

Developed Billing Snaps System for the feasibility of IESCO employees.