I'm an MS in Computer Science student at UMass Amherst and a former AI/Data Engineer at Deloitte, building at the intersection of applied AI, NLP systems, data platforms, and agentic workflows.

I’m especially interested in:

• LLM systems and evaluation
• retrieval, memory, and reasoning workflows
• graph + agent orchestration
• production-grade data and ML infrastructure
• AI products that need reliability, explainability, and real-world usefulness

My recent work has focused on turning AI ideas into usable systems:

• Multi-agent reasoning and debate systems for training-free self-improvement, reflection, and reasoning analysis
• RAG-based research copilots that retrieve papers, summarize findings, cluster themes, and reduce manual literature review
• Graph-native clinical reasoning prototypes using Neo4j and agent orchestration for explainable, patient-specific follow-up support
• Portfolio and product prototypes that present research, projects, and technical work clearly for real users

Explores multi-agent debate, self-reflection, and training-free self-improvement in language models, including GRPO-inspired feedback loops and reasoning dynamics.

A multi-agent research assistant built with LangGraph, LangChain, and MCP for paper retrieval, summarization, clustering, and visualization.

A graph-native prototype for explainable, patient-specific follow-up reasoning in head & neck care, combining guideline-style reasoning with anatomy-aware context.

A portfolio site built with Next.js, React, TypeScript, and Tailwind CSS to showcase my AI systems work, NLP/retrieval projects, data engineering background, and publications.

Languages: Python, SQL, TypeScript, Java, C++
AI/ML: PyTorch, LangChain, LangGraph, RAG pipelines, LLM evaluation, NLP
Data & Infra: Spark, Databricks, Airflow, AWS, ETL/ELT, data pipelines
Apps & Tools: React, Next.js, Tailwind CSS, Streamlit, Neo4j, Git, Vercel

I’m currently interested in roles where I can work on:

• applied AI engineering
• AI/ML infrastructure
• LLM products and evaluation systems
• data platforms for intelligent applications
• software roles with strong technical ownership

I enjoy writing about AI systems, memory, reasoning, and practical implementation ideas alongside building them.

• LinkedIn: linkedin.com/in/noshitha-juttu
• Hugging Face: huggingface.co/Noshitha98
• Portfolio: portfolio/noshitha-juttu

I like building systems that don’t just generate output, but reason better, retrieve better, and hold up better in real use.