CV

Professional Profile

Language engineer with expertise in NLP system architecture, multilingual infrastructure development, and machine learning pipelines. I apply engineering principles and linguistic knowledge to design, build, and optimize scalable language technologies for diverse applications.

Technical Skills

Software Engineering & Development

• Languages: Python, Java, C/C++, Kotlin
• Backend: Django, SQL, REST APIs, Docker
• Frontend: HTML/CSS/JavaScript, Andriod Development
• Tools: Git, AWS, Unix/Linux, Jupyter
• Text Processing: Regex, Parsing Tools

NLP & Machine Learning

• Frameworks: PyTorch, TensorFlow, BERT, Hugging Face
• Libraries: scikit-learn, NLTK, spaCy, NumPy, Pandas
• Applications: NLP Pipeline Development, Machine Translation, LLM Validation, Language Modeling

Multilingual Technologies & Research

• Analysis Tools: ELAN, CLAN, Praat
• Data Tools: R, Corpus Analysis Tools
• Research Methods: Experimental Design, Statistical Modeling, Cross-linguistic Analysis

Professional Experience

Language Engineer | AWS

• NLP pipeline development, LLM validation workflows, multilingual model evaluation, and system optimization for large language models (LLMs)

Machine Learning Data Linguist | AWS

• Prompt enigneering, machine learning data annotation, multilingual model training and evaluation, and optimization for large language models (LLMs)

Software QA Specialist | Apple

• Software UI/UX and localization testing, automation, and machine translation evaluation

Clinical Research Data Coordinator | UCSF Neurology

• Automated data pipelines, validation systems, and multilingual data extraction
• Related Publication: Speaking in Tones: The role of lexical tones in Chinese-speaking Primary Progressive Aphasia

Research Engineer | Columbia University

• Machine learning pipelines, data visualization, and real-time data systems
• Publication: Probing the Imaginable: Shared and Distinct Processes Between Imagery and Perception Across Semantic Domains

Research Data Analyst | City University of Hong Kong

• Automation for linguistic annotation, cross-linguistic analysis, and transcription systems
• Corpus: CHILDES Mandarin-Cantonese-English EACMC Corpus
• Related Publication: Grammatical development of the native L1 in Cantonese–English bilingual children: early costs and long-term gains

Education

• MS Computer Science, University of Texas at Austin, Expected 2026
• BA Linguistics and Computer Science, Columbia University, 2024

Full version available upon request