About Prasanth Janardhanan
I’m Prasanth Janardhanan — AI Developer, LLM Systems Architect, and ML Researcher with 15+ years of engineering experience. I specialise in production LLM systems, agentic RAG pipelines, and AI agent infrastructure.
Projects
gomcpgo — An open-source Go framework for building MCP (Model Context Protocol) servers. MCP is now a Linux Foundation standard under the Agentic AI Foundation. I’ve published 12+ MCP servers using the framework.
Braille OCR Transcriber — The first ML model for Grade 2 contracted Braille OCR. A ByT5 seq2seq model achieving 92.9% exact match on real-world Braille, 9x better than existing baselines. Published on Hugging Face.
EU AI Act Compliance Navigator — An agentic RAG system that classifies AI systems by risk tier under the EU AI Act and generates citation-backed compliance checklists. Built in Go with hybrid search and an MCP server interface.
See more on the projects page and my GitHub.
Core Skills
- AI / LLM: RAG Pipelines, Agentic AI, MCP, AI Agent Design, Prompt Engineering, LLM Fine-tuning (LoRA/QLoRA), Vector Databases
- AI Governance: EU AI Act, Responsible AI Design, Explainable AI, SOC2, Regulatory Compliance
- ML & Frameworks: Python, PyTorch, Hugging Face Transformers, Seq2Seq Fine-tuning, ByT5, YOLOv8
- Languages: Go / Golang (Expert), Python, TypeScript
- Infrastructure: AWS, GCP, Docker, Kubernetes, Terraform
Get in Touch
- Email: prasanthmj at gmail.com
- GitHub