AI Engineer | Machine Learning | Deep Learning
I build end-to-end AI systems that solve practical problems using machine learning, deep learning, and large language models. I enjoy working across the entire pipeline—from data preparation and model development to deployment and user-facing applications.
I particularly enjoy solving concrete problems with neural networks and building intelligent systems that create measurable impact.
- Strong foundation in machine learning, statistics, and data analysis.
- Experience building production-style AI applications and end-to-end ML workflows.
- Interested in deep learning, natural language processing, computer vision, and agentic systems.
- Focused on understanding the problem before selecting models or technologies.
- Committed to building reproducible, maintainable, and business-oriented solutions.
- Python
- SQL
- Pandas
- NumPy
- Power BI
- Regression and Classification
- Clustering and Customer Segmentation
- Random Forest
- XGBoost
- Support Vector Machines
- K-Nearest Neighbors
- Feature Engineering
- Hyperparameter Optimization
- Statistical Analysis and Hypothesis Testing
- TensorFlow
- Keras
- Convolutional Neural Networks
- Natural Language Processing
- Retrieval-Augmented Generation (RAG)
- Large Language Models
- Multi-Agent Systems
- Git and GitHub
- Jupyter Notebook
- VS Code
- MySQL
- Streamlit
- LangChain
- FAISS
- Ollama
- Groq API
Built a domain-specific conversational assistant using Retrieval-Augmented Generation. Implemented FAISS vector search, local embeddings with Ollama, and Groq-hosted LLMs to provide accurate, context-aware responses through a Streamlit application.
Technologies: Python, LangChain, FAISS, Ollama, Groq, Streamlit
Developed a collaborative AI agent framework consisting of specialized web and finance agents capable of tool usage, information retrieval, and financial analysis using real-time market data.
Technologies: Phi Framework, Groq, DuckDuckGo, Yahoo Finance, Agent Orchestration
Designed an NLP pipeline to discover and group related news events using sentence embeddings and unsupervised learning techniques. Generated event timelines and automated labeling for improved information discovery.
Technologies: Python, NLP, Sentence Embeddings, Scikit-learn, Clustering
Built an end-to-end machine learning pipeline for predicting customer loan default risk, including data preprocessing, feature engineering, model selection, and hyperparameter optimization.
Technologies: Python, Scikit-learn, XGBoost, Random Forest
Implemented deep learning models for plant disease classification and evaluated custom CNN architectures alongside transfer learning approaches.
Technologies: TensorFlow, Keras, Computer Vision
Analyzed customer purchasing patterns and developed interactive dashboards to support data-driven business decisions and customer segmentation.
Technologies: Python, SQL, Power BI
- Deep Learning
- Neural Networks
- Large Language Models
- Retrieval-Augmented Generation
- Agentic AI Systems
- Natural Language Processing
- Computer Vision
- AI Application Development
- MLOps and Deployment
LinkedIn: https://www.linkedin.com/in/praband-kumar-t-40405a3b0
Email: praband10@gmail.com