2025
Isabelle Ng
Computer Science • Data Science • Music — UC Berkeley
I am a final-year undergraduate at UC Berkeley interested in building interpretable, efficient natural language systems that enable stronger human-AI collaboration. My most recent work involves designing and evaluating agentic LLM systems that combine evolutionary search with inference-time refinement, with applications to text-to-SQL. I am currently seeking advisors and applying to PhD and MS programs for the next cycle. I'll be at NeurIPS 2025 - happy to chat about research and potential advising fits.
NLP
Agentic LLMs
AI Engineering
Machine Learning
Interpretability
Publications & Preprints
2025
ProRefine: Inference-Time Prompt Refinement with Textual Feedback
Deepak Pandita, Tharindu Cyril Weerasooriya, Ankit Parag Shah, Isabelle Diana May-Xin Ng, Christopher M. Homan, Wei Wei • NeurIPS 2025 Efficient Reasoning Workshop, 2026 AAAI Student Abstract
Research & Industry Experience
People Analytics AI Development Intern
Oracle · Remote · Sep 2025 – Present
- Developing a GenAI-powered copilot that analyzes unstructured employee data to support more informed decisions in hiring, engagement, and collaboration.
- Building predictive models to assess manager effectiveness and uncover leading indicators of high-performing managers.
GenAI Research Engineering Intern
Accenture, Center for Advanced AI · Mountain View, CA · Jun 2025 – Aug 2025
- Led research and development of MultiGA, a novel evolutionary prompting framework for multi-LLM collaboration on reasoning tasks such as text-to-SQL and trip planning.
- Developed an experimental pipeline enabling automated agentic experiments with remote metric collection and evaluation.
NLP Student Researcher
UC Berkeley School of Information · Berkeley, CA · Jan 2025 – May 2025
- Analyzed 1,500 legal cases using LLMs to study judicial reasoning around Section 230 under UCB/Stanford JD-PhD mentorship.
- Identified interpretive patterns with implications for legislative reform; project recognized with Best Poster at UC Berkeley's Research Symposium.
- See Berkeley I School news coverage here.
Machine Learning Engineering Intern
H2O.ai · Mountain View, CA · Jun 2024 – Aug 2024
- Built a Retrieval-Augmented Generation (RAG) chatbot to assist employees with technical queries about H2O.ai products.
- Integrated Python APIs for H2O Wave and H2O GPT Enterprise, engineering a query controller that routes questions by product type.
- Improved internal knowledge discovery and documentation accessibility across teams.
Data Engineering Consultant
Mattel · Remote · Sep 2024 – Jan 2025
- Assessed Mattel's enterprise data ecosystem and designed a scalable ESG data pipeline supporting sustainability initiatives.
- Conducted stakeholder interviews and identified infrastructure discrepancies across divisions.
- Developed recommendations to centralize analytics workflows in Google BigQuery and improve governance and access protocols.
LLM Development Intern
Conagra Brands · Remote · Jan 2024 – May 2024
- Created an AI chatbot powered by PrivateGPT and Ollama to extract insights from investor call data.
- Assisted the backend team with data preprocessing and designed the user-facing interface using Gradio.
Teaching
I have served as a teaching assistant and course leader for Berkeley’s core computer science and data science curricula, with responsibilities spanning lecture development, infrastructure, and pedagogy design.
| Term | Course | Role |
|---|---|---|
| Spring 2026 | Data C88C — Computational Structures in Data Science | uGSI (Head Teaching Assistant, 20 hrs/week) |
| Fall 2025 | Data C88C — Computational Structures in Data Science [Guest Lecture on Efficiency] [Trees] | uGSI (Head Teaching Assistant, 20 hrs/week) |
| Spring 2025 | Data C88C — Computational Structures in Data Science | uGSI (Lead Teaching Assistant, 12 hrs/week) |
| Fall 2024 | Data C88C — Computational Structures in Data Science | uGSI (Teaching Assistant, 8 hrs/week) |
| Summer 2024 | CS 61A — Structure and Interpretation of Computer Programs | uGSI (Teaching Assistant, 20 hrs/week) |
Leadership & Service
- Software Product @ Cal — Cofounder & President (Aug 2024 – May 2025). Established the first undergraduate organization for software product management at UC Berkeley, fostering collaboration among engineers, designers, and business students. Organized the 2025 Global AI Products Summit and led cross-disciplinary mentorship and fellowship programs focused on product innovation.
- Data Science Society at Berkeley — Vice President (Jan. 2025 - Present). Directed community and culture initiatives, coordinating career fairs, technical workshops, and networking events for data science students.
Contact
Email: isabelle.ng@berkeley.edu
GitHub: isabe11eng · LinkedIn: /in/isabelle-ng-185875262/ · OpenReview: profile
© 2025 Isabelle Ng