Skip to content
View dattang12's full-sized avatar
🎯
Focusing
🎯
Focusing
4 followers · 4 following
  • San Francisco, CA
  • 13:57 (UTC -12:00)
  • LinkedIn in/dattang12

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Sharkx2Achievement: YOLOAchievement: Quickdraw

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Sharkx2Achievement: YOLOAchievement: Quickdraw

Block or report dattang12

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
dattang12/README.md

Hi there, I'm Dat 👋

CS student at San Jose State University building full-stack intelligent AI systems. Currently seeking internships in Software Engineering or AI Engineering.

🤖 What I'm working on

Building AI Agent & Multi-Agent systems — designing autonomous workflows, tool-use pipelines, and orchestrated agent frameworks that solve real-world problems.

🔑 Key Projects

  • 🏆 Top 3 Finalist at Stanford x GoogleDeepmind Hackathon 2026 – ApplyWisely: AI-powered job application tracker that extracts job details from screenshots using Gemini 2.0 Flash and auto-updates statuses via Gmail Agent
  • 🏆 Top 2 Finalist at IBM Ethical AI Hackathon 2025 – EthicsLens: AI-powered document ethics analyzer built on IBM watsonx that scans documents for bias, fairness violations, and ethical risks using Granite LLM with explainable compliance scoring
  • ⭐ GreenChecker: Autonomous GitHub issue-fixing agent with sandboxed test verification!!!
  • Structured-Extraction-Eval: LoRA fine-tuning of Qwen2.5-0.5B for schema-conformant JSON extraction — FSM-constrained decoding via outlines, 2.16M trainable params (0.44% of model), 2×2 evaluation separating format compliance from correctness
  • NemotronIQ: Multi-agent company intelligence system — 5 autonomous agents deliver BUY/HOLD/SELL decisions in 30 seconds
  • InsightRAG: Hierarchical RAG pipeline with semantic chunking and vector search over 5,000+ indexed document chunks

🛠 Tech stack

Python FastAPI LangChain LangGraph OpenAI Anthropic Claude CrewAI AutoGen React TypeScript PostgreSQL Qdrant Docker AWS Pinecone

🏢 Organizations

MyRecommendation   Leechyapporg   MyRecommendation  

🌱 Open Source Contributions

  • traceroot-ai — Open-source observability and self-healing layer for AI agents (YC S25)

📫 Connect with me

LinkedIn GitHub Instagram Discord

Open to internship opportunities — feel free to reach out!

Pinned Loading

  1. ApplyWisely-v0 ApplyWisely-v0 Public

    AI Gmail Agent that scans screenshots and monitors your Gmail to update applications automatically by "1 click button"

    JavaScript 3

  2. Structured-Extraction-Eval Structured-Extraction-Eval Public

    LoRA fine-tuning + evaluation framework for structured JSON extraction, measuring schema validity and correctness separately.

    Python

  3. GreenChecker GreenChecker Public

    Autonomous GitHub issue-fixing agent with sandboxed test verification

    Python 2

  4. InsightRAG InsightRAG Public

    RAG system for chatting with PDFs and YouTube videos, with automatic page and timestamp citations.

    Python

  5. NemotronIQ NemotronIQ Public

    Multi-agent company intelligence dashboard with BUY/HOLD/SELL verdicts, powered by NVIDIA Nemotron.

    JavaScript

  6. JobMatching JobMatching Public

    AI-powered job matching platform — upload your resume, get ranked job recommendations by AI Agent

    TypeScript