Summary:

• 5+ years of professional experience in data science model development, MLOps pipeline automation, and production cloud deployments.
• Strong expertise in Python programming with ML libraries including Scikit-learn, Pandas, TensorFlow, and deep learning frameworks.
• Hands-on experience in exploratory data analysis (EDA), large dataset preprocessing, and model lifecycle management.
• Proficient in AWS services (SageMaker, Lambda, EC2) and Azure for scalable model deployment and monitoring.
• Excellent problem-solving abilities and proven collaboration skills with cross-functional teams including data scientists and engineers.

Skills:

• Languages: Python, SQL, AIML, RAG, LLM
• Frameworks: Scikit-learn, TensorFlow, Keras, PyTorch, Flask, FastAPI, LangChain, Hugging Face
• Databases: PostgreSQL, MongoDB, InfluxDB, Qdrant
• Cloud / MLOps: AWS (SageMaker, Lambda, EC2), Azure, Docker, Kubernetes, CI/CD
• Data Processing: Pandas, NumPy, EDA, Entity Extraction, Time Series
• Version Control: Git, GitHub, GitLab
• APIs: RESTful APIs, GraphQL APIs
• Generative AI: OpenAI GPT-4, Custom LLMs, RAG

Projects:

Retrieval-Augmented Generation Chatbot for Business Knowledge

Technologies Used: Python, OpenAI GPT-4, LangChain, Qdrant, FastAPI, Docker, Azure, AWS, Git.

Project Description: Developed an enterprise-grade AI chatbot system designed to extract actionable business insights from large document repositories using advanced LLM technology and vector database architecture for semantic search and knowledge retrieval.

Responsibility:

• Designed and implemented end-to-end machine learning models for document processing and knowledge extraction.
• Built automated MLOps pipelines for model retraining, monitoring, and performance optimization.
• Performed comprehensive EDA on large document datasets and implemented preprocessing workflows.
• Deployed scalable production systems on AWS and Azure using containerization and CI/CD practices.
• Collaborated with data scientists and backend engineers to ensure seamless integration and optimal performance.

Generative AI Recipe Insights Recommender

Technologies Used: Python, Scikit-learn, TensorFlow, Azure, FastAPI, Docker, Vector Search, REST APIs.

Project Description: Built a personalized recommendation engine leveraging Generative AI and vector similarity search to provide intelligent recipe, wine, and cocktail suggestions based on user preferences and behavioral patterns.

Responsibility:

• Developed and optimized machine learning recommendation algorithms using deep learning frameworks.
• Implemented automated model retraining pipelines with real-time deployment capabilities.
• Conducted extensive data analysis and preprocessing for recommendation accuracy improvement.
• Created scalable REST APIs for frontend integration and real-time recommendation serving.
• Executed end-to-end POCs and research for algorithm improvement and business value enhancement.

Stock Prediction and Business Forecasting System

Technologies Used: Python, LSTM, RNN, TensorFlow, InfluxDB, Azure, AWS EC2, Time Series Analysis, Statistical Modeling.

Project Description: Engineered comprehensive time series forecasting solution for stock market prediction and business KPI forecasting using advanced deep learning models and automated pipeline architecture for continuous model improvement.

Responsibility:

• Designed and trained LSTM/RNN models for time series analysis and forecasting applications.
• Built automated data pipelines for continuous model retraining and performance monitoring.
• Performed statistical modeling and deep learning model optimization for production deployment.
• Deployed scalable cloud solutions on AWS EC2 and Azure with database integration.
• Conducted research and experimentation to improve model performance and business outcomes.