╔══════════════════════════════════════════════════════════════╗
║ ║
║ CHINMAY JOSHI · FOUNDER & AI/ML ENGINEER ║
║ ║
╚══════════════════════════════════════════════════════════════╝
I'm a Founder-Engineer currently building ORIXEN.AI — an AI revenue automation company serving real clients.
My day-to-day work lives at the intersection of LLM evaluation, RAG observability, and production GenAI systems. I don't just prototype — I ship pipelines that clients depend on.
Currently in my 7th semester of B.Tech AI & Data Science at ADYPU Pune, graduating 2027.
chinmay = {
"role": "Founder & AI/ML Engineer",
"company": "ORIXEN.AI → orixenai.in",
"focus": ["LLM Evaluation", "RAG Observability", "GenAI Pipelines"],
"stack": ["FastAPI", "LangChain", "GPT-4", "Docker", "AWS", "Azure"],
"certified": "Microsoft Azure AI Engineer Associate",
"sih": "Top Qualifier 2024 & 2025",
"location": "Pune, India | Open to Remote / Relocate",
"open_to": "Internships · Full-time · Collaborations"
}AI/ML & GenAI
Backend & Infrastructure
Frontend & Full-Stack
|
Production-grade LLM evaluation system with hallucination scoring, context faithfulness checks, and observability dashboards.
|
Multi-agent enterprise assistant with RAG backend, tool-use, and role-based access control.
|
|
Real-time adaptive traffic control using computer vision and reinforcement learning. SIH qualifier project.
|
Real-time monitoring for LLM pipelines — latency, token cost, and quality drift tracking.
|
- 🏗️ Shipping AI pipelines at ORIXEN.AI — working with real clients
- 📖 Deep-diving into LLM evaluation frameworks and observability tooling
- 🔍 Open to AI/ML internships and GenAI engineering roles
- ✍️ Writing about applied AI on Medium and LinkedIn