Skip to content
View khangle2101's full-sized avatar
  • Linh Chieu, Thu Duc
  • 10:20 (UTC +07:00)

Block or report khangle2101

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
khangle2101/README.md

Le Hoang Khang

AI Engineer focused on Prompt Engineering, RAG pipelines, and LLM application development — building evaluation-driven AI systems from design to deployment.

B.Eng. in Automation & Control Engineering Technology (HCMUTE) | GPA: 3.4/4.0

GitHub LinkedIn YouTube Email


What I Do

  • Prompt Engineering — Design specialized prompts (system/role, structured JSON output, temperature tuning, context grounding) and iterate based on evaluation metrics
  • RAG Pipeline Development — Build end-to-end retrieval-augmented generation systems: semantic chunking, query rewriting, multi-query retrieval, LLM re-ranking
  • LLM Integration — OpenAI/OpenRouter APIs, LangChain, streaming, Pydantic structured outputs, cost-aware model selection
  • Edge AI & Computer Vision — Real-time detection on constrained hardware (Jetson Nano, TensorRT)

Tech Stack

Python OpenAI LangChain ChromaDB Pydantic Gradio PyTorch OpenCV TensorRT Docker SQL Git


Featured Projects

Advanced RAG Knowledge Assistant

Prompt Engineering | RAG | LLM APIs | Evaluation-Driven Development

  • Designed 4 specialized prompts (chunking, rewriting, re-ranking, answer generation) with per-task temperature tuning and structured JSON output
  • Achieved MRR 0.929, Accuracy 4.79/5 — a +24.8% improvement over a LangChain baseline
  • Implemented cost-aware model selection, context grounding, streaming chat, and incremental document management
  • Benchmarked with 150 test questions using MRR, nDCG, keyword coverage, and LLM-as-judge scoring

Repo: advanced-rag-chatbot | Demo Video

AI-Powered Customer Feedback Automation

AI Classification | REST APIs | Workflow Automation

  • End-to-end automation processing customer feedback with AI-powered sentiment analysis and categorization (OpenRouter)
  • Integrated Google Apps Script, n8n, Telegram Bot via REST APIs and webhooks
  • < 5 seconds processing time per submission with logging, retry logic, and status tracking

Repo: feedback-automation-ai

Real-Time Fire & Smoke Detection Drone (Edge AI)

Computer Vision | TensorRT | Jetson Nano | MAVLink

  • Two-stage cascaded detection (smoke → fire confirmation) to reduce false positives
  • Jetson Nano deployment with TensorRT FP16; 10+ FPS inference
  • Data fusion: detections + Pixhawk telemetry for geo-tagged alerts + autonomous LOITER

Repo: Real-Time-Fire-Smoke-Detection-Drone

SCARA 3-DOF Robot Arm — Color Sorting (Vision + Kinematics)

Computer Vision | Robotics | MATLAB

  • HSV segmentation + calibration (pixel → mm) for pick coordinates
  • MATLAB forward/inverse kinematics, Arduino stepper control
  • Includes Unknown rejection case to avoid misclassification

Repo: SCARA-Color-Sorting

Popular repositories Loading

  1. Application-of-Image-Processing-and-3-DOF-SCARA-Robotic-Arm-in-Object-Classification-Based-on-Color Application-of-Image-Processing-and-3-DOF-SCARA-Robotic-Arm-in-Object-Classification-Based-on-Color Public

    3-DOF SCARA robot sorts colored objects using computer vision and MATLAB-based control.

    MATLAB 7 3

  2. Real-Time-Fire-Smoke-Detection-Drone Real-Time-Fire-Smoke-Detection-Drone Public

    This project develops an automated forest fire surveillance system using UAV drones, combining Artificial Intelligence (AI) with the YOLOv11 model optimized by TensorRT to run on NVIDIA Jetson Nano.

    Python 4 1

  3. khangle2101 khangle2101 Public

    3

  4. Real-Time-Traffic-Signs-Classification-using-CNN-OpenCV Real-Time-Traffic-Signs-Classification-using-CNN-OpenCV Public

    Real-time traffic sign classification using CNNs. Trained on Google Colab, runs via webcam with OpenCV.

    Jupyter Notebook 3 1

  5. Vehicle-Tracking-and-Counting-with-YOLOv8-and-Supervision Vehicle-Tracking-and-Counting-with-YOLOv8-and-Supervision Public

    Vehicle detection, tracking, and counting in video using YOLOv8 and Supervision. Built with Python, OpenCV, and Ultralytics.

    Jupyter Notebook 3

  6. feedback-automation-ai feedback-automation-ai Public

    AI-powered customer feedback automation system using n8n, Google Apps Script, and OpenRouter

    JavaScript 1