Building intelligent systems | AI, LLMs, Full Stack | Open to collaboration

💫 About Me

AI Engineer focused on shipping LLM-powered products that actually work in production. I've optimized inference pipelines to cut costs by 60%, built RAG systems hitting 95% accuracy, and designed agentic workflows that scale. What gets me excited: Taking a messy real-world problem, architecting an AI solution, and watching it handle edge cases I didn't even anticipate. 🎯 Core Focus 🧠 LLMs & RAG — Fine-tuning, prompt engineering, retrieval optimization 🤖 Agentic AI — Multi-agent systems, tool-use, autonomous workflows ⚡ Production ML — Low-latency inference, cost-efficient scaling, MLOps 🔧 Full Stack — End-to-end delivery from model to user interface

---

🎯 Currently Available For

---

🌐 Connect With Me

---

🏅 Certifications

---

🧠 Tech Stack

🤖 AI, ML & GenAI

Vector Databases:

Data Science:

---

💻 Development Stack

Languages:

Frontend:

Backend:

Databases:

---

☁️ Cloud, DevOps & MLOps

Cloud Platforms:

DevOps & CI/CD:

MLOps:

Tools:

---

🔬 Currently Exploring

---

🎯 Featured Projects

🏥 Wellnix	🏠 MaidEase	🤖 AgentFlow
AI-powered Health & Wellness	Smart Home Services Platform	Agentic AI Workflow Builder
Personalized health recommendations with intelligent symptom analysis	Smart marketplace with AI-powered service matching & seamless booking	Visual workflow builder with multi-agent orchestration & tool-use

---

🏆 Key Achievements

⚡ 40% Faster	💰 60% Cheaper	🎯 95% Accurate	🚀 10x Scale
LLM Inference	Token Processing	RAG Systems	System Capacity
Model quantization, distillation & KV cache optimization	Efficient chunking & embedding compression	Hybrid retrieval with re-ranking pipelines	Enterprise microservices at 100K+ requests

---

📊 GitHub Stats

---

🏅 Achievements

💡 Open to collaborating on innovative AI projects that push the boundaries of what's possible.

_{^{Last updated: January 2026}}