I am a recent Master's graduate in Computer Science and Engineering from the University at Buffalo, specializing in the practical application of technology to address real-world challenges. My expertise encompasses Generative AI, Machine Learning, Chain of Thoughts Prompting, and LLM Customization (FT and RLHF with Reasoning).
- 🔭 I’m currently working on AI Agents centered on Blockchain applications.
- 🌱 I’m currently learning more about Langgraph and Langchain.
- 👯 I’m looking to collaborate on projects involving AI Agents and LLM Development.
- 🤔 I’m looking for help with optimizing AI-infused search systems.
- 💬 Ask me about: Web Apps, Machine Learning, AI Agents, MCP, Blockchain & NFTs.
- 📫 How to reach me: anirudhms247@gmail.com
- 😄 Pronouns: He/Him
- ⚡ Fun fact: I recently fine-tuned the Qwen3‑1.7B language model on a physics reasoning benchmark using GRPO and Chain‑of‑Thought prompting, achieving significant gains in symbolic accuracy and reasoning trace quality.
- Developed a real-time cryptocurrency monitoring agent using Pydantic-AI and a local Llama 3.2 model, capable of fetching, analyzing, and validating market data from CoinGecko.
- Integrated Supabase for automated storage and updating of top 50 cryptocurrency prices, ensuring accurate and consistent data syncing in realtime.
- Implemented a Model Context Protocol (MCP) server to enable Claude Desktop to perform CRUD operations on the crypto database, using FastMCP and secure environment configuration.
- Designed robust error handling, environment-driven configurations, and optimized SQL schema with indexing for scalable and reliable market monitoring.
- Utilized the Qwen-3-1.7B language model with Group Relative Policy Optimization (GRPO) and Chain-of-Thought (CoT) prompting on a physics benchmark dataset.
- This approach improved the model's reasoning and alignment with human-like problem-solving.
- The integration of GRPO and CoT led to a 12% increase in model accuracy on the physics benchmark.
- Designed a system that integrates Apache Solr's indexed Wikipedia data with AI for efficient knowledge retrieval and summarization.
- Developed a web crawler to scrape and preprocess 55,000 data points and ETL them into JSON format.
- Built a React-based website with DialoGPT for querying, hosted on the Google Cloud Platform.
-
SIITR: A Semantic Infused Intelligent Approach for Tag Recommendation
- A tag recommendation system using similarity measures and SVM, achieving 94.48% accuracy.
- Presented at ANTIC 2021 and published in Springer. : https://link.springer.com/chapter/10.1007/978-3-030-96040-7_31
-
ISBRNM: Integrative Approach for Semantically Driven Blog Recommendation Using Novel Measures
- A blog recommendation system using NLP, GRUs, and optimization techniques, with 95.85% accuracy.
- Presented at ICDTA 2022 and published in Springer. : https://link.springer.com/chapter/10.1007/978-3-031-02447-4_2