Hi, I'm
Aakriti Poudel

~ Making machines think, one agent at a time ~

I build Agentic AI systems, RAG pipelines, and computer vision models from Kathmandu, Nepal. Final year Computer Engineering student at Kathmandu University · GPA 3.89/4.0

Aakriti Poudel
LangChain Agentic RAG PyTorch YOLO FastAPI ChromaDB MLflow Docker AWS Transformer Architecture Multi-Agent Orchestration PostgreSQL Redis OpenCV AR / Vuforia ESP32 / IoT LangChain Agentic RAG PyTorch YOLO FastAPI ChromaDB MLflow Docker AWS Transformer Architecture Multi-Agent Orchestration PostgreSQL Redis OpenCV AR / Vuforia ESP32 / IoT
📌 About Me

A bit about me

I'm an AI Engineer from Kathmandu who loves building systems that actually think — not just predict. My work sits at the intersection of LLMs, computer vision, and practical engineering. I've shipped production RAG systems, trained YOLO models for live video streams, built 8-node agentic pipelines, and implemented Transformer architectures from scratch just to understand what's happening under the hood.

When I'm not coding, I'm organizing hackathons, mentoring peers on AI/cloud, or obsessively reading research papers. I believe great AI is built with both rigour and curiosity — and a little bit of chaos.

1.5+
Years building AI
10+
Projects shipped
3.9
GPA (out of 4.0)
500+
Hackathon participants led
💼 Experience

Where I've worked

ML Engineer

Kyra Works Pvt Ltd
Oct 2025 – Mar 2026 · Full-time

AI Engineer

Freelance · Remote / Contract
Dec 2024 – Aug 2025 · Contract | Mar 2026 – Present
🚀 Projects

Things I've built

DocumentQuery Bot

DocumentQuery Bot

Enterprise RAG with intent-aware query routing — classifies each query (factual / comparative / summary) before selecting a handler, reducing unnecessary LLM calls.

LangChainChromaDB Gemini 2.5HuggingFaceStreamlit
Diabetes Prediction

Diabetes Prediction Pipeline

Full supervised + unsupervised ML pipeline on 1,000-patient clinical data — EDA, feature engineering, classification (99.5% accuracy!) and patient risk stratification.

Scikit-learnXGBoost K-MeansPandas
Transformer NLP

Transformer NLP + SHAP

Full Transformer from scratch in PyTorch on 50k+ docs — multi-head attention, positional encoding, SentencePiece. Linear SHAP for token-level explainability maps.

PyTorchSentencePieceSHAP
PatchIt

PatchIt — Pothole Detection

YOLOv8 detecting potholes from live ESP32-CAM feeds, integrated with a web dashboard for municipal authorities. Real-world CV on edge hardware.

YOLOv8React Node.jsESP32
Swarm Robotics

Swarm Robotics — Disaster Search

Multi-agent robotic system with ESP32s, motor drivers & ultrasonic sensors for search & rescue. Swarm communication via MQTT + camera for target detection & obstacle avoidance.

ESP32MQTT CoppeliaSimCVIoT
DigiTour AR

DigiTour — AR Heritage Guide

AR Android app using Vuforia + Google Cloud Anchors to guide users through Panauti's heritage sites with digital storytelling, 3D overlays, and interactive experiences.

VuforiaGoogle Cloud Anchors ARCoreCVAugmented Reality
Sign AI
🏆 KU HackFest Winner

Sign AI — ASL Recognition

Real-time recognition of 25+ ASL gestures with YOLOv5. Won Education Category at KU HackFest 2023 — Nepal's largest hackathon with 500+ participants.

YOLOv5React PythonComputer Vision
🌟 Recognition & Leadership

Beyond the code

🏆
KU HackFest 2023 — Education Category Winner

Built Sign AI, a real-time ASL gesture recognition system (YOLOv5), and won Nepal's largest in-person hackathon with 500+ participants.

🎓
NAAMII Full Scholarship — 6th Nepal Annual AI School (ANAIS)

Competitively selected for an 11-day intensive AI program covering LLMs, agents, geometric deep learning, and AI for healthcare.

📢
Microsoft Learn Student Ambassador (MLSA) · 2023–2025

Organised AI/ML and cloud workshops for 100+ peers. Built technical communication and documentation habits directly carried into engineering practice.

KU HackFest Organising Committee · 2022 & 2024

Coordinated Nepal's largest hackathon across two editions — managing 500+ participants, cross-functional teams, and sponsor relations.

📜
Certifications

Associate Data Scientist · DataCamp  |  Supervised ML · Andrew Ng, Coursera  |  Intro to Statistics · Stanford, Coursera

📄 Research

Publications & Research

🔬 Work in Progress

Research paper coming soon...

Currently working on a research paper. Details will be added here once submitted / published. Watch this space — good things take time to bake! ☕

📍 Topic area: AI / Machine Learning
📅 Status: In progress
📖 Venue: TBD

🎬 Tech Blog

My Tech Blog

Sharing what I build, learn, and break — from Kathmandu to the internet.

RAG System Blog Thumbnail
Building a RAG system from scratch
Read blog↗
Transformers Blog Thumbnail
How Transformers actually work
Read blog↗
ESP32 Blog Thumbnail
YOLO on an ESP32: Edge AI for ₹500
Read blog↗

Want to build something cool?

I'm open to full-time roles, freelance projects, and interesting collaborations.
I reply to every email — promise!

Made with ✏️ & ☕ in Kathmandu · aakritipoudel.com.np