I'm a Data Scientist specializing in Document Intelligence and Large Language Models. My work focuses on building robust document processing pipelines and developing efficient information retrieval systems. I'm particularly passionate about:
- 📄 Document AI and multimodal transformers
- 🔍 Information retrieval and indexing systems
- 🤖 LLM reasoning and Chain of Thought approaches
- 🌱 Exploring new architectures in RAG design patterns
- 🧠 Experimenting with reasoning models (DeepSeek-R1)
- 📚 Improving document indexing and retrieval systems
- 🔄 Chain of Thought implementations
- 🖼️ Vision transformer architectures for document understanding
- 🐍 Python
- 📊 SQL
- 🤖 RAG Pipelines
- 🧠 LLMs (Open source and Closed source)
- 💡 Prompt Engineering
- 🎯 Fine-tuning (PEFT, LoRA)
- 🔄 RLHF
- 🔥 PyTorch
- ⚡ TensorFlow
- 📚 Scikit-learn
- 🔗 LangChain
- 📖 LlamaIndex
- 🔍 Qdrant
- 🎯 Vespa
- 📊 FAISS
- 💾 PostgreSQL
- 🍃 MongoDB
- ☁️ AWS
- 🔷 Azure AI Studio
- ⚡ Azure Functions
- 🐳 Docker
- 📂 Git
- 📄 Document Layout Analysis
- 📝 OCR
- 🎯 Object Detection
- 👁️ Vision Transformers
- 🧠 CNN
- 📈 Statistics
- 🔬 Scientific Research
- 🤖 Supervised Learning
- 🎯 Unsupervised Learning
- 👥 Active volunteer in community development initiatives
- 🌱 Interested in technology for social impact
