I am currently working as a Senior Web Solutions Engineer at Google gTech team. I have a YouTube channel where I post content related to Machine Learning, Artificial Intelligence and Software Engineering. I also maintain an Engineering Newsletter Systems That Scale which is subscribed by 30K+ Engineers and Students.

• 🌿 LLMs from scratch: Language Modeling core concepts and architecture optimizations from scratch.
• HuggingFace BPE Tokenizer Visualizer: Visualize HuggingFace Byte-Pair Encoding tokenizer encoding process.
• ⛳ Fine-tune LLM collection: Collection of notebooks for Fine-tuning LLMs from scratch.
• 🦁 Toy Transformer: A decoder only Transformer implementing masked attention from scratch (Pytorch).
• 🎪 Tiny Stories SLM: Reproduce Small Language Model (SLM) trained on Tiny Stories dataset from this paper.
• AI Engineering 101: The repo holds the collection of Agentic workflows as a part of my Youtube channel's playlist.
• 📈 Deep Research Reflect Evolve: My paper (Sequential Research Plan Refinement and Candidates Crossover).
• 📚 Static Deep Research Agent: My paper (Tree-based approach for creating Configurable and Static Deep Research Agent).
• 📝 LangPost: An AI agent that creates a Linkedin post from a Linkedin newsletter article or any other blog post.
• ⛅ LangGraph Adaptive RAG: Implementing Adaptive RAG in LangChain using OpenAI module.
• ⛄ My LLD Template: The repository holds the implementation of Low Level Design Patterns in Java.
• 🍀 My DSA Template: The repository holds the implementation of many basic and advanced DSAs in Java.

• Distributed Systems 101: A playlist on Distributed Systems where we will talk about concepts like Replication, Transactions, Databases internals, Partitioning and many more from scratch.
• RAG and LangChain - Building Multi-agent workflows: Let's build a multi-agent workflow in LangGraph from scratch.
• AI Engineering 101: All about AI Engineering, Agentic Workflows and Orchestration from scratch

• Deep Researcher Reflect Evolve: Deep Researcher with Sequential Plan Reflection and Candidates Crossover.
• Static-DRA: A Hierarchical Tree-based approach for creating Configurable and Static Deep Research Agent.