Master's student in Cybersecurity at NTU Singapore, working at the intersection of AI, security, and product design. I translate technical capabilities into practical, user-oriented solutions — LLM applications, RAG architectures, and backend systems that emphasize reliability, scalability, and data privacy in sensitive domains.
About
Experience
Experience
AI Product Associate Intern
- Partnered with the customer-success team and stakeholders to replace fragmented controls and a flat 1700+ voice catalog with a guided voice-and-character configuration workspace; translated needs into 50+ PRDs and interactive prototypes, aligned scope with design and engineering, and shipped 5 production pages.
- Led a cross-product UX redesign across 20+ pages, running 7 parallel AI agents alongside interactive prototypes to cut navigation friction and resolve 400+ UI inconsistencies and 10+ UX issues across information architecture, components, and outdated copy.
- Turned recurring support feedback on mispronounced local names into a measurable product initiative — a 349-entry benchmark and blind evaluation workflow, then productization of the pronunciation component — lifting usable accuracy from 78.0% to 93.8% across 321 unique terms (+15.8 pp).
- Worked directly with emergency-department staff and clinicians at a public hospital to translate bedside requirements and 6 deployment constraints into a 90-minute workshop, then prioritised and drove delivery of a 20-language, hands-free Translation Assistant with consent, recording, and access controls.
Researcher (Part-time)
- Built a RAG-based internal Q&A system over policy and process documents.
- KNN retrieval on long-document corpora; scenario-grounded evaluation reaching 96% Recall@N and 4.4/5 answer relevance.
Researcher (Part-time)
- Multi-agent reinforcement learning (A2C-based) for large-scale microservice scheduling.
- Validated on real-world ByteDance and Alibaba traces; co-authored publication in Expert Systems with Applications.
Product Manager Intern
- Led a 6-member cross-functional team to design and deliver a 6–7 page inventory product through to final acceptance, owning requirements, prioritisation, development coordination, testing, and delivery.
- Designed the core inventory workflows — inbound, outbound, inventory query, stock alerts, reconciliation, and discrepancy handling — and shipped 4 frontend, backend, and AI features, including Qwen-powered daily reports surfacing stock movements, low-inventory risks, and stale inventory.
Education
Nanyang Technological University
Singapore
Xi'an Jiaotong University
Xi'an, China
Publications
Ma, N., Tang, A., Xiong, Z., & Jiang, F. (2025). A deep multi-agent reinforcement learning approach for the micro-service migration problem with affinity in the cloud. Expert Systems with Applications, 273, 126856.
Selected Work
01
SayExact · Voice Pipeline Accuracy Adapter
An accuracy adapter for voice pipelines, grown out of an earlier production project. Prioritised fields by error rate × business impact to isolate the highest-value use case, redesigned the capture flow, and validated it through user testing — lifting ASR accuracy past 85%. Taken from concept to internal pilot as a LiveKit Agents adapter with 336 automated tests; an upstream limitation found along the way was fixed and contributed back to the 14K-star repository.
02
MindGap · Claude Code Plugin
A Claude Code plugin that measures where each turn's wall time actually goes — Claude wait, automated tools, or user-gated tools. Zero-dependency Node.js hooks log every UserPromptSubmit / PreToolUse / PostToolUse / Stop to JSONL; a paired skill aggregates per-turn timings on demand. Published to the Claude Code marketplace under MIT.
03
AI Data Visualization Workflow Tool
End-to-end LLM workflow that unifies parsing, cleaning, analysis, and visualization across heterogeneous data (PDF / Excel / CSV). Compresses multi-hour analyst work to ~10 minutes; deployed as a Lark bot for zero-setup access. Built with Coze.
Skill Index
- 01 Product Management
- 02 LLM
- 03 RAG
- 04 AI Agent
- 05 Prompt Engineering
- 06 Workflow Design
- 07 Reinforcement Learning
- 08 Coze · FastGPT
- 09 Python
- 10 TypeScript
- 11 Java
- 12 Spring Boot
- 13 SQL
- 14 PostgreSQL
- 15 MongoDB
- 16 Jira
- 17 Figma
- 18 Lark
- 19 Cybersecurity
hover to reveal connections