# Minh Duân Trần

Minh Duân Trần is a remote worker on Himalayas, AI Model Evaluator & LLM Alignment Specialist at Outlier.ai, based in Vietnam.

Source: https://himalayas.app/@minhduntrn

```text
AI Model Evaluator at Outlier.ai who evaluated frontier LLM and speech-to-speech outputs for accuracy, safety, and instruction following.
```

| Detail | Value |
| --- | --- |
| Availability | Looking for a job |
| Location | Vietnam |
| Authorized to work in | Vietnam |
| Salary expectations | 30k+ USD |
| Job categories | AI Model Evaluator |
| Skills | LLM Evaluation, RLHF, Side By Side Ranking, Hallucination Analysis, Safety Auditing, Audio and Multimodal Evaluation, ASR, TTS, OCR, Data Annotation, Ground Truth, Rubric Engineering, Text Normalization, LaTeX, React Native |
| GitHub | https://github.com/tuyen-coder |

## About

```text
At Outlier.ai, I evaluated and ranked multi-turn outputs from frontier large language models and speech-to-speech systems using side-by-side comparisons to support RLHF.

I analyzed text and audio outputs for factual hallucinations, safety issues, reasoning flaws, ASR/TTS defects, and prompt adherence, then wrote evidence-based rationales against project rubrics.

For the Bahnar OCR & Document Digitization Project at HCMUT, I transcribed document scans into ground-truth data and checked text normalization and spatial accuracy.

I also developed a Smart Home IoT System project with React Native, Expo Router, and WebSockets, and reproduced Elsevier’s Journal of Algebra layout in LaTeX for an academic typesetting commission.
```

## Experience

### AI Model Evaluator & LLM Alignment Specialist

[Outlier.ai](https://himalayas.app/companies/outlier-ai). Aug 2026 - Oct 2026

```text
Evaluated and ranked multi-turn outputs of frontier LLMs and Speech-to-Speech systems via Side-by-Side comparisons to support RLHF. Conducted error and safety analysis across text and audio modalities, and authored structured rationales in compliance with project rubrics.
```

Skills: LLM-Evaluation, RLHF, SxS-Ranking, Hallucination-Detection, Safety-Auditing, ASR-TTS, Prompt-Adherence, Rubric-Compliance

### Data Annotation & Quality Assurance Contributor

Bahnar OCR & Document Digitization Project (HCMUT). Sep 2023 - Nov 2023

```text
Transcribed low-resource Bahnar text from document scans to build ground-truth datasets for OCR and vision-to-text models. Executed text normalization and spatial proofreading, enforcing data integrity and annotation consistency.
```

Skills: Data-Annotation, OCR-Ground-Truth, Text-Normalization, Quality-Assurance, Low-Resource-Languages, Document-Digitization

## Education

### Ho Chi Minh City University of Technology (HCMUT)

Bachelor of Computer Science, Computer Science. 2023 - Present

```text
Pursuing a Bachelor of Computer Science with an expected graduation in November 2027.
```

## Tech stack

- GitHub
- React Native
- JavaScript
- Python
- C++
- C
- Git
- SQL
- Audacity

To contact Minh Duân, message them from this profile with a Himalayas employer account: [Hire on Himalayas](https://himalayas.app/hire).

## People also viewed

- [Thang nguyen User](https://himalayas.app/@thangnguyenuser): Video Instruction Creator, Softage Technology
- [Ngoc Nguyen](https://himalayas.app/@ngocnguyen): Voice Recording Specialist, Mercor Intelligence
- [Lê Hoàng](https://himalayas.app/@lhong): AI Assisted Research & Data Analysis, Independent
- [Alice Nguyen](https://himalayas.app/@alicenguyen): Graphic Designer, Shady Eyewear
- [Yin Tsing](https://himalayas.app/@yintsing): AI Training Contributor, Outlier AI
- [kudo shinichi](https://himalayas.app/@kudoshinichi): Quantitative Research Consultant & AI Systems Architect, WorldQuant BRAIN
- [Thiên Phú User](https://himalayas.app/@thinphuser): AI Data Quality Contributor, Mindrift / OneForma
- [Anh Ha Hoang](https://himalayas.app/@anhhahoang): Full Stack Developer Intern, Ignify
- [Trường Sơn](https://himalayas.app/@trngsn): Lead Content Annotator & Technical Developer, LinguaFlow Platform
- [Hoàng Long Đoàn](https://himalayas.app/@honglongon): Vision Language Models in Medical Image Segmentation, HUST Lab
