Projects

Building a cost-effective, secure AI automation agent for domain-specific tasks. Focused on fine-tuning compact LLMs with retrieval-augmented generation, tool mapping, and compliance considerations. Exploring efficient ways to build specialized agents that understand domain context and reasoning patterns.

Co-architected production-grade infrastructure for building reliable agentic systems. Contributed to memory systems (working, episodic, semantic), evaluation pipelines, and deployment reliability features. Focus on making AI agents production-ready with proper testing and monitoring.

Built an intelligent assistant for 500+ Linux shortcuts using RAG pipeline. Engineered vector embeddings and generative AI to answer natural language queries from man pages with high accuracy. Demonstrates practical application of retrieval-augmented generation for documentation search.

Implemented a fully functional Transformer architecture from scratch in PyTorch. Built multi-head self-attention, positional encoding, and encoder-decoder components. Benchmarked on sequence tasks and evaluated the impact of hyperparameter tuning on model performance.

Built distributed ML pipeline for sentiment analysis on 14M+ song lyrics, achieving 92% accuracy and 40% faster processing. Leveraged Hadoop ecosystem with Spark, PySpark, MapReduce, and HDFS for scalable data processing. Demonstrates expertise in big data engineering and distributed computing.

User-friendly apartment search application with natural language query interface. Built preference parsing system, intelligent ranking algorithms, and application guidance features to simplify the housing search experience.