● Responsible for analyzing data and creating big data engineering pipelines using technologies such as Azure MLOps, PostgreSQL DB, and Azure Data Factory to ensure a smooth flow of the overall project through the integration of agile practices.● Collaborated with business leadership to comprehensively assess and gather project requirements, ensuring a thorough understanding of both back-end and front-end needs aligned with company criteria.● Developed tree-based machine learning models such as Decision Tree, XGBoost, and AdaBoost, achieving excellent performance metrics to extract the most important features from the provided data.● Utilized clustering algorithms such as k-means, k-prototype, and hierarchical clustering to group customers or data based on similar patterns.● Created Power BI and Power Apps dashboard to show the output.● Leveraged various BERT and HuggingFace transformers for NLP-based tasks, including text summarization, named-entity recognition, and the creation of complex text classification models and stored the json output in PostgreSQL DB.● Used Docker to containerize multiple projects across different systems, leveraging Docker’s engine compatibility with various operating systems and cloud platforms.● Managed Kubernetes to deploy and manage API services independently, enhancing the resilience and scalability of applications.

● Develop algorithms for information extraction and finding patterns from structured, semi-structured, and unstructured documents.● Engaged in effective communication with clients and team members to define processes, enhance work quality, and propose AI integration with ongoing projects, contributing to compelling pitches for client consideration.● Solely responsible for developing equations used to calculate the credit scores of bank customers using the XGBoost model.● Responsible for creating the entire data pipeline for the project and deploying it on an AWS EC2 instance after containerization in Docker.● Performed live stock price prediction using a model composed of LSTM+CNN layers to achieve optimal results.● Utilized SQL queries for data retrieval from various databases and performed data munging in Apache Spark.

● Responsible for managing a team of interns and building a project using Apache Kafka to send restaurant reviews individually to interns for accurate classification tagging.● Responsible for analyzing text data from various sources, perform data pre-processing and creating a complex restaurant review classification model using an ensemble of multiple machine learning and deep learning algorithms, including Gradient Boost, LSTM, Logistic Regression, and Multinomial Naive Bayes, yielding remarkable results.● Managed AWS S3 buckets and SQL server by writing cron jobs to update the machine learning models and data provided every 24 hours.● Developed Docker images of projects and deployed them on AWS EC2 instances.● Utilized AWS SageMaker for a secure and streamlined model development process, encompassing data gathering through to deployment in the AWS environment.● Designed the entire project using various tools and technologies such as Apache Spark, the Elasticsearch, Logstash, Kibana, and Hive, ensuring smooth and uninterrupted operation.