I bridge the gap between high-level research and production-ready engineering. My work focuses on building Agentic Workflows, Secure AI Infrastructure, and Scalable Software Systems that solve real-world problems.
I am currently researching and implementing autonomous reasoning loops that move beyond linear RAG.
- The Goal: Transforming static LLM implementations into dynamic, self-correcting agents.
- The Stack: LangChain (LCEL), Llama 3.3 (Groq), ChromaDB, and Custom JSON Output Parsing.
| Intelligent Systems | Security & Robustness | Systems Architecture |
|---|---|---|
| Agentic Orchestration | Adversarial Machine Learning | Distributed Systems Thinking |
| RAG Pipeline Optimization | Model Guardrailing & Safety | High-Performance FastAPI Backends |
| Fine-tuning & Embeddings | Secure SDLC Integration | Cloud-Native Scalability |
🏗️ Featured System: Meridian Policy Intelligence
A full-stack RAG application designed for high-precision corporate policy retrieval.
- Key Metric: Achieved 96% Citation Accuracy and 93.5% Groundedness.
- The Innovation: Implementation of a "Guardrail Prompt Template" and local CPU-based HuggingFace embeddings for cost-effective inference.
- Design: Editorial/Brutalist UI built with Vanilla HTML/CSS.
View Repository | View Live App
I am currently pursuing advanced studies in Software Engineering and Intelligent Computing Systems. My approach is defined by:
- Research-Driven Engineering: Applying academic rigor to production code.
- Security-First AI: Protecting intelligent systems against data poisoning and prompt injection.
- Scalable Craftsmanship: Writing code that isn't just "smart," but maintainable at scale.
- Languages: Python (Expert), TypeScript, Go, SQL.
- AI/ML: LangChain, PyTorch, HuggingFace, ChromaDB, Groq.
- DevOps/Backend: FastAPI, Docker, Kubernetes, AWS/Heroku.
- Security: Ethical Hacking, OWASP Top 10 for LLMs.