AI/ML Engineer focused on building practical machine learning and generative AI systems across RAG, vector search, semantic retrieval, ML pipelines, and data driven applications.
I enjoy turning messy data, documents, and business requirements into useful AI products, from feature engineering and model evaluation to backend APIs, vector databases, and deployed user facing applications.
- Building full stack GenAI applications with FastAPI, Streamlit, Pinecone, Gemini, Grok, and Docker
- Designing Retrieval Augmented Generation systems with semantic embeddings and vector search
- Developing ML pipelines for classification, anomaly detection, and predictive analytics
- Evaluating models using precision, recall, F1, AUC ROC, and RAG quality metrics
- Deploying AI applications on cloud and container based platforms
A deployed full stack RAG application that allows users to upload PDF, TXT, and DOCX documents, index them into Pinecone, and ask natural language questions over uploaded content.
Live Demo: https://huggingface.co/spaces/bhuvaneswari2620/enterprise-document-intelligence-engine
Repository: https://github.com/bhuvana2620/Enterprise-AI-Document-Intelligence-Engine
Tech Stack: Python, FastAPI, Streamlit, Pinecone, SentenceTransformers, Google Gemini, optional xAI Grok fallback, Docker, Hugging Face Spaces
Highlights
- Built document upload, extraction, chunking, embedding, retrieval, and answer generation pipeline
- Used Pinecone namespaces to isolate uploaded documents by browser session
- Deployed the application as a Docker based Hugging Face Space
- Added manual session cleanup and documented future TTL based cleanup for abandoned sessions
- Included custom evaluation hooks for RAG quality testing
Backend API platform for managing API access, routing, authentication, and service workflows.
Focus: backend engineering, REST APIs, authentication, API gateway design, cloud deployment
Financial analytics dashboard for investment risk analysis, portfolio insights, and data visualization.
Focus: data analysis, financial metrics, dashboarding, Python based analytics
Languages: Python, SQL, R, PySpark, JavaScript Machine Learning: Classification, Regression, Clustering, Anomaly Detection, Feature Engineering, Model Evaluation GenAI and NLP: RAG, LLMs, Prompt Engineering, Semantic Search, Embeddings, Vector Databases Frameworks: Scikit learn, TensorFlow, PyTorch, Hugging Face Transformers, XGBoost, LightGBM Vector Databases: Pinecone, FAISS, Chroma Backend and APIs: FastAPI, REST APIs, Streamlit Cloud and MLOps: AWS, SageMaker, Docker, GitHub Actions, MLflow, ETL Pipelines Visualization: Power BI, Tableau, Matplotlib, Seaborn, Plotly
I am targeting roles in:
- AI Engineer
- Machine Learning Engineer
- Generative AI Engineer
- LLM Application Engineer
- Software Engineer, AI/ML
- Backend Engineer, AI Platform