
I build RAG-powered chatbots, web dashboards, and AI search systems for businesses | Python, OpenAI, Pinecone
그들의 링크와 프로필의 나머지 부분을 살펴보고 그들이 누구인지 알아보세요. Zinn Hub는 모든 Zinner의 프로필을 공개하고 투명하게 유지합니다 — 신뢰를 구축하고 자신감 있게 고용할 수 있습니다.
AKORA는 Zinn Hub에 자신의 기술을 입증하고 작업 증거를 제공했습니다. 모든 검증된 Zinner는 실습 품질 보증 검토를 통과하므로 안심하고 고용할 수 있습니다.
🛡️ October 2026부터 인증됨
I am an AI Engineer who builds intelligent systems that help businesses unlock the value hidden inside their own data. My specialty is Retrieval-Augmented Generation (RAG) — the technology that transforms static documents, PDFs, and knowledge bases into interactive, AI-powered assistants that answer questions in plain English.
I discovered my passion for AI engineering through an intensive, hands-on scholarship program where I completed a comprehensive track covering the entire modern AI stack. Through this journey, I built multiple working systems from scratch — not just tutorials, but real, functional applications. I learned how to architect RAG pipelines, manage vector databases, engineer effective prompts, and deploy AI tools that solve actual problems.
제가 만들어 드릴 수 있는 것:
RAG-Powered Chatbots: AI assistants that read your documents and answer customer or employee questions accurately, with citations to the original source.
Semantic Search Engines: Search tools that find information by meaning, not just keywords — so your team finds what they need even when they don't know the exact words.
Document Q&A Systems: Turn your PDFs, manuals, and knowledge bases into an instant-answer system that saves hours of manual searching.
Interactive AI Apps: User-friendly Streamlit applications that make your AI tools accessible to anyone, no technical skills required.
Data Processing Pipelines: Automated scripts that clean, batch, and prepare your data for AI systems using Pandas and NumPy.
My Technical Toolkit:
Python, Pandas, NumPy, OpenAI API (Embeddings, Chat Completions, Function Calling, Responses API), Pinecone, ChromaDB, LangChain, Streamlit, t-SNE, Matplotlib, Git, and REST API integration.
작업 방식:
I believe in clean, working solutions — not overcomplicated theory. I communicate clearly, deliver on time, and focus on understanding your actual problem before writing a single line of code. Whether you need a small prototype to test an idea or a complete system to automate a workflow, I will work with you to build something that genuinely helps.
I am early in my freelance journey, which means you get dedicated attention, competitive rates, and a genuine commitment to your project's success. I am not here to collect a paycheck — I am here to build a reputation, one happy client at a time.
If you have a document-heavy workflow, a customer support challenge, or an idea for an AI tool, let's talk. Send me a message and tell me what you're trying to solve. I will tell you honestly whether I can help — and if I can, I will give it everything I have.
이 프리랜서가 전문으로 하는 기술 및 전문 지식입니다.
이 프리랜서가 이용 가능한 서비스 지역입니다.
Built a semantic search engine that finds similar customer reviews based on meaning, not just keywords. What it does: Processes thousands of e-commerce clothing reviews from a CSV dataset Generates embeddings using OpenAI's API and stores them in ChromaDB Applies t-SNE dimensionality reduction to visualize review clusters in 2D Implements a search function that returns the 3 most semantically similar reviews to any query Demonstrates real-world applications like automated feedback categorization (Quality, Fit, Style, Comfort) Tech Stack: Python, ChromaDB, OpenAI Embeddings, Pandas, NumPy, scikit-learn (t-SNE), Matplotlib
자세히 보기 →Built a semantic search engine that finds similar customer reviews based on meaning, not just keywords. What it does: Processes thousands of e-commerce clothing reviews from a CSV dataset Generates embeddings using OpenAI's API and stores them in ChromaDB Applies t-SNE dimensionality reduction to visualize review clusters in 2D Implements a search function that returns the 3 most semantically similar reviews to any query Demonstrates real-world applications like automated feedback categorization (Quality, Fit, Style, Comfort) Tech Stack: Python, ChromaDB, OpenAI Embeddings, Pandas, NumPy, scikit-learn (t-SNE), Matplotlib
자세히 보기 →Built a semantic search engine that finds similar customer reviews based on meaning, not just keywords. What it does: Processes thousands of e-commerce clothing reviews from a CSV dataset Generates embeddings using OpenAI's API and stores them in ChromaDB Applies t-SNE dimensionality reduction to visualize review clusters in 2D Implements a search function that returns the 3 most semantically similar reviews to any query Demonstrates real-world applications like automated feedback categorization (Quality, Fit, Style, Comfort) Tech Stack: Python, ChromaDB, OpenAI Embeddings, Pandas, NumPy, scikit-learn (t-SNE), Matplotlib
자세히 보기 →Built a semantic search engine that finds similar customer reviews based on meaning, not just keywords. What it does: Processes thousands of e-commerce clothing reviews from a CSV dataset Generates embeddings using OpenAI's API and stores them in ChromaDB Applies t-SNE dimensionality reduction to visualize review clusters in 2D Implements a search function that returns the 3 most semantically similar reviews to any query Demonstrates real-world applications like automated feedback categorization (Quality, Fit, Style, Comfort) Tech Stack: Python, ChromaDB, OpenAI Embeddings, Pandas, NumPy, scikit-learn (t-SNE), Matplotlib
자세히 보기 →Built a semantic search engine that finds similar customer reviews based on meaning, not just keywords. What it does: Processes thousands of e-commerce clothing reviews from a CSV dataset Generates embeddings using OpenAI's API and stores them in ChromaDB Applies t-SNE dimensionality reduction to visualize review clusters in 2D Implements a search function that returns the 3 most semantically similar reviews to any query Demonstrates real-world applications like automated feedback categorization (Quality, Fit, Style, Comfort) Tech Stack: Python, ChromaDB, OpenAI Embeddings, Pandas, NumPy, scikit-learn (t-SNE), Matplotlib
자세히 보기 →Built a semantic search engine that finds similar customer reviews based on meaning, not just keywords. What it does: Processes thousands of e-commerce clothing reviews from a CSV dataset Generates embeddings using OpenAI's API and stores them in ChromaDB Applies t-SNE dimensionality reduction to visualize review clusters in 2D Implements a search function that returns the 3 most semantically similar reviews to any query Demonstrates real-world applications like automated feedback categorization (Quality, Fit, Style, Comfort) Tech Stack: Python, ChromaDB, OpenAI Embeddings, Pandas, NumPy, scikit-learn (t-SNE), Matplotlib
자세히 보기 →Built a semantic search engine that finds similar customer reviews based on meaning, not just keywords. What it does: Processes thousands of e-commerce clothing reviews from a CSV dataset Generates embeddings using OpenAI's API and stores them in ChromaDB Applies t-SNE dimensionality reduction to visualize review clusters in 2D Implements a search function that returns the 3 most semantically similar reviews to any query Demonstrates real-world applications like automated feedback categorization (Quality, Fit, Style, Comfort) Tech Stack: Python, ChromaDB, OpenAI Embeddings, Pandas, NumPy, scikit-learn (t-SNE), Matplotlib
자세히 보기 →장바구니에 다른 Zinner의 Zinns가 포함되어 있습니다. 한 번에 하나의 Zinner에서만 주문할 수 있습니다.
장바구니를 비우고 이 Zinn 을(를) 추가하시겠습니까, 아니면 현재 주문으로 먼저 결제하시겠습니까?
Zinn Hub 앱 다운로드
알림 · 빠른 접근 · 전체 화면
브라우저에서 공유를 탭하세요
➜ 그 다음 "홈 화면에 추가"를 탭하세요