SWE @ DIS · CS @ NTU

Audric Yap

Builder across different domains, consistently using AI to compress time-to-output, explore solution space faster, and ship more.

AI-native
Builder
Iterative
Workflow-driven

"Turning LLMs into leverage."

[Work]

01

AI Marking Assistant

active build

Automate essay and short-answer grading with AI-powered evaluation against structured rubrics, while keeping teachers in control.

#Next.js#tRPC#Cloudflare_Workers#Gemini_API#Prisma#message_queues
02

Distributed Data Pipeline Platform

deployed

Ingest, process, and deliver continuous data streams with event-driven orchestration and configurable retention.

#Python#TypeScript#C##gRPC#Kafka#MinIO#Kubernetes
03

Helix (Investment Knowledge Base)

active build

Turn scattered AI research conversations into a structured, queryable investment thesis repository with automated price tracking.

#Python#Pydantic#SQLite#yfinance#GitHub_Actions#CLI
04

AI Mafia (Multi-Agent Simulation)

prototype or internal

Autonomous AI agents play social deduction games, demonstrating multi-agent coordination, strategic deception, and complex state management.

#TypeScript#Vercel_AI_SDK#React#Ink#Zod#multi-agent

[About]

CS student at NTU, SWE at DIS; I build software and adapt: systems-heavy when needed, feature-heavy when it matters.

I build with AI as a force multiplier across my entire workflow, not just in the final product. I use it to reason faster, explore alternatives, and compress iteration cycles, while keeping judgment and responsibility human. I also care about shipping usable tools and refining them under real use, not demos that only work in best-case conditions.

Beyond featured projects: shipped personal tools with AWS (ECS, CDK), Flask/Celery, and web automation.

Singapore

Python, TypeScript, Next.js, K8s, LLM APIs

[Contact]

Get in touch.

Open to discussions regarding AI-native products, high-leverage tooling, and hard technical problems.