Screening of drug compounds to predict success rate based on biological factors. This includes R&D discovery technologies.Drug Recommendation | Building Next Generation Black box Decision EngineMATCh Next Generation Engine: Analyzing the Drugs Descriptions, conditions, reviews and then recommending the medicines. Utilized advanced algorithms and machine learning techniques to personalize medication recommendations based on individual patient profiles.Explainable AI: Developed and deployed models that not only make accurate drug recommendations but also provide understandable explanations for the suggested medicines. Incorporated rule-based approaches, feature importance analysis, and visualizations to enhance the transparency and trustworthiness of the AI system.

Pioneered and actively managing an ML community dedicated to nurturing thought-provoking discussions and debates on the societal impact of AI. Empower beginners and intermediate learners with curated YouTube and Discord content, delivering valuable resources and expert guidance.Discord Channel Link : https://discord.gg/6VVp99yswFYoutube Link: https://www.youtube.com/channel/UCsb5-7RnEN2oeOqSskKvyOw

Personalize in a Box : Worked on building one-click deployment frameworks in programmatical way for:1. Recommender systems using Python, Terraform on AWS Personalize.2. Time Series forecasting for sales using AWS forecast3. Anomaly Detection using Amazon L4M.Analytics Accelerator: Utilized Dockerized environments to construct a CDC Data-stack, incorporating tools such as Airbyte, Airflow, DBT, and PostGre SQL.Built PyTorch models for Image Classification tasks, leveraging the power of deep learning to accurately clas- sify images. Configured and deployed the models on AWS, creating endpoints to serve predictions and enable real-time inference.* Tools / Tech Stack * : Python, Terraform, Airbyte, Air-flow, MYSQL, Dockers, AWS services- Sage Maker, Amazon Lex, Personalize, Lambda Functions, Amazon Forecast & Anomaly Detection, Octavia , CI/CD.

• Driving projects from an architecture & framework point of view in the Machine Learning Team.• ML Framework: Developed a highly scalable and distributed ML framework for ETL jobs, incorporating automatic re-processing and achieving 100% automation. Leveraged end-to-end pipelines and automated systems in Python to deploy simplified solutions at scale.• Sales Forecast: Improved sales forecasting by implementing a custom Statistical Quantile approach, boosting model performance by 20% and optimizing time. Optimized overall performance through design choices, including stateless machines and idempotent algorithms.• Recommender Systems: Building Personalized Recommender systems for suggestions of sales products to end-users. Used Hierarchical clustering & Ranking methods for Similarity, Relevance score generation.• Explainable AI (EDA): Developed and implemented an Explainable AI Dashboard to enhance model inter-pretability and transparency for stakeholders.- Tools / Technologies Used: Python, CI/CD pipelines (ETL jobs), Kibana, MySQL, Jenkins, AWS-S3, Machine Learning Algorithms - XGBoost , Random Forest, Other Classification & Clustering Approaches.

I was exposed to the various activities in the Machine Learning domain using Python. Worked on designing a data pipeline to make it easy to do feature engineering & build ML models.Knowledge and usage of the open source machine learning frameworks available on the market, like Tensorflow, Python ML and others.Knowledge of Feature Vector Construction. Implementing Neural Networks, Predictive models, Regression, Recommendation Engines, and many more skills.