Nero Un
Software Engineer & IT Consultant, focusing on Software Development, Data Science, and Generative AI.
This profile was put together from Nero's public GitHub portfolio, and they haven't joined Vibetown yet, so reach them through their portfolio. Is this you? Contact us to update or remove it.
About
Nero Un works in AI engineering and ML & data science, based in Taiwan, Taipei (IBM Taiwan). Software Engineer & IT Consultant, focusing on Software Development, Data Science, and Generative AI. Public projects on GitHub include Guardian Llm Benchmark (Dedicated to building a benchmark ranking that compares different Guardian LLMs / LLMs used for Guardian…), 2025 Pycon Tw Ai Guardrails (This repository contains the implementation and benchmarking framework for AI Guardrails, specifically…) and Defect Detection And Segment Deep Learning (Detection and Segmentation in Powder Spreading Process of Magnetic Material Additive Manufacturing), mostly written in Python, Jupyter and TypeScript.
Projects 6
- github.com
Guardian Llm Benchmark
Dedicated to building a benchmark ranking that compares different Guardian LLMs / LLMs used for Guardian tasks, supporting providers from HuggingFace and OpenRouter.
- github.com
2025 Pycon Tw Ai Guardrails
This repository contains the implementation and benchmarking framework for AI Guardrails, specifically focusing on hallucination detection in Large Language Models (LLMs). The project was developed for PyCon Taiwan 2025 presentation on AI safety and reliability.
- github.com
Defect Detection And Segment Deep Learning
Detection and Segmentation in Powder Spreading Process of Magnetic Material Additive Manufacturing
- github.com
Machine Learning Metrics Calculator
A web-base calculator to calculate the metics with confusion matrix, such as recall, accuracy, precision, etc.
- github.com
Nvidia-Nemo-DataDesigner-Tutorial
A Tutorial notebook with Nvidia Nemo DataDesigner
- github.com
Mlops Best Practice
MLOps best practice focus on model training performance monitoring, built pipeline, and model serving. Using Sci-kit Learn, MLFlow, Prefect, and BentoML.