You will get AI systems to extract insights from your business data
Rising Talent
Rising Talent
Project details
I build production ready AI pipelines that turn raw data into structured insights and knowledge graphs. With 8 years of AI/ML experience and real-world delivery for enterprise clients, I specialize in web crawling, LLM-based data extraction, and graph database integration.
My local GPU infrastructure (RTX 4090) means no cloud API costs and 100% data privacy — making my solutions up to 95% cheaper than cloud-based alternatives.
Whether you need to automate document processing, extract entities from web data, or build a knowledge graph from scratch, I deliver clean, scalable, production-ready systems.
My local GPU infrastructure (RTX 4090) means no cloud API costs and 100% data privacy — making my solutions up to 95% cheaper than cloud-based alternatives.
Whether you need to automate document processing, extract entities from web data, or build a knowledge graph from scratch, I deliver clean, scalable, production-ready systems.
AI Algorithms
Large Language Model, Transformer ModelAI Applications
AI Chatbot, Natural Language Generation, Natural Language UnderstandingAI Development Language
PythonAI Tools
Azure OpenAI, Hugging FaceAI Models
ChatGPT, GPT-4, LLaMA, WhisperWhat's included
| Service Tiers |
Starter
$800
|
Standard
$2,000
|
Advanced
$6,000
|
|---|---|---|---|
| Delivery Time | 7 days | 14 days | 30 days |
Number of Revisions | 1 | 2 | 3 |
AI Model Integration | |||
Batch Normalization | - | ||
Database Integration | - | ||
Detailed Code Comments | - | - | |
Image Upscaling | - | - | - |
MLOps | - | - | - |
Model Deployment | - | ||
Model Documentation | - | - | |
Model Monitoring | - | - | |
Model Testing & Optimization | - | - | |
Model Tuning | - | - | - |
Natural Language Processing | - | ||
NLP Tokenization | - | - | - |
Pre-Training | - | - | - |
Prompt Engineering | |||
Setup File | - | - | - |
Source Code |
Optional add-ons
You can add these on the next page.
Fast Delivery
+$400 - $2,500Frequently asked questions
About Tae
Graph RAG & AI Agent Specialist | LangGraph | Ex-Scenera (Netflix)
Seoul, South Korea - 1:22 am local time
Recent work:
- LG Energy Solution (Jan to Apr 2026): LangGraph and Crawl4AI multi-agent talent data automation pipeline. Replaced manual sourcing and screening workflows end-to-end.
- Legal document search system: retrieval time cut from 5 hours to 40 minutes using LLM-based natural language query
- 2asy.ai: Causal-chain news intelligence on global macro events. Built on Graph RAG (events-over-entities architecture). Runs 13 times per day with zero human intervention, roughly 95 percent cost reduction versus cloud APIs.
Production delivery at Scenera (2023 to 2025) for Netflix, Sony, GS Retail, and LG Science Park. Computer vision pipelines, predictive maintenance systems, and natural-language-to-SQL agents.
Core stack: LangGraph, LangChain, Neo4j, vLLM, LiteLLM, FastAPI, Crawl4AI, Pinecone, OpenAI, Claude, Elasticsearch.
I work as a single technical owner. Design, implementation, deployment, no handoff gaps. Direct accountability from architecture through production.
M.Sc. Seoul National University. 2 patents in AI optimization.
Time zone: Korea, Japan, Europe overlap preferred. Flexible for US East Coast morning hours.
Steps for completing your project
After purchasing the project, send requirements so Tae can start the project.
Delivery time starts when Tae receives requirements from you.
Tae works on your project following the steps below.
Revisions may occur after the delivery date.
Requirements analysis
Analyze your data source, define extraction goals, and confirm expected output format
Pipeline development
Build crawling and data ingestion pipeline tailored to your data source