Skip to content
View Praciller's full-sized avatar
0 followers · 3 following

Block or report Praciller

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.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. 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
Praciller/README.md

Pakon Poomson

AI Engineer | GenAI Engineer | Data Engineer | RAG & Agentic Workflows

Portfolio Email LinkedIn

About

I am an AI Engineer at Seagate Technology focused on practical GenAI automation, internal engineering workflow tooling, and backend/data infrastructure. My current work includes multi-agent AI workflows for requirements analysis, debugging, testing, and PR preparation, plus C# internal software, VictoriaMetrics TSDB setup, and Kafka-to-TSDB ingestion validation with Apache Flink/Java.

Previously, I built full-stack applications and internal automation tools with React, Next.js, FastAPI, PostgreSQL, Directus, Supabase, and Docker. I focus on turning AI prototypes into usable software: reliable APIs, clean data flows, practical UX, and deployment-ready architecture.

Role Focus

Priority Target roles Evidence in this profile
1 AI Engineer RAG apps, LLM agents, multimodal extraction, AI automation, evaluation-minded delivery
2 GenAI Engineer / Data Engineer LangChain, OpenAI, Gemini, pgvector, PostgreSQL, Kafka/Flink validation, VictoriaMetrics
3 Data Science / Data Analyst / Full-Stack / Frontend ML projects, analytics dashboards, React/Next.js, FastAPI, SQL, dashboards, API integrations

Core Stack

Area Tools and Strengths
AI / ML Python, TensorFlow, PyTorch, scikit-learn, LLMs, RAG, LangChain, OpenAI, Gemini, Ollama, prompt engineering
Data / Infrastructure Apache Kafka, Apache Flink, VictoriaMetrics, PostgreSQL, pgvector, Redis, SQL, time-series data, ingestion validation
Software Engineering TypeScript, Next.js, React, Node.js, FastAPI, C#, Java, Docker, CI/CD, Git/GitLab, REST APIs
Applied AI Agentic workflows, computer vision, OCR/entity extraction, multilingual summarization, document retrieval, structured AI outputs

Selected AI Credentials

  • AIAT Super AI Engineer Season 6: Foundation AI (Theory) - Artificial Intelligence Association of Thailand, 2026
  • Anthropic Academy certificates across Claude API, Claude Code, Model Context Protocol, subagents, agent skills, and AI Fluency
  • Google Cloud AI/ML skill badges across Vertex AI, Gemini, Imagen, Multimodal RAG, BigQuery ML, Document AI, and ML APIs
  • AIS Academy Prompt Engineering & Agentic AI

Featured AI Projects

Project Why it matters Stack
Wellness AI Assistant Production-style RAG chatbot with document ingestion, vector search, authenticated chat, streaming responses, and tool-calling patterns Next.js, TypeScript, LangChain, Supabase, PostgreSQL, pgvector, OpenAI
Receipt AI Expense Tracker Multimodal receipt parser that extracts structured JSON from Thai/English receipts and visualizes spending analytics Next.js, Gemini Vision, Supabase, Recharts
AI Resume Matcher Resume/JD matching tool with PDF parsing, structured extraction, skill-gap analysis, career guidance, and interview prep React, Python, FastAPI, Gemini, Vercel
AI Product Listing Assistant Image-to-product-listing generator with multilingual output, FastAPI backend, retry/circuit-breaker patterns, and test coverage Python, FastAPI, Streamlit, Gemini Vision, pytest
Customer Support AI System Multimodal support-ticket analysis for category, sentiment, priority, and response drafting React, FastAPI, Gemini, Playwright, pytest

Current Focus

  • Building GenAI workflow automation for requirements analysis, debugging, testing, and PR preparation.
  • Shipping RAG, multimodal AI, and agentic applications with production-minded APIs and data flows.
  • Strengthening backend/data infrastructure with time-series storage, Kafka/Flink validation, and PostgreSQL/pgvector.
  • Hardening AI applications with better evaluation, observability, testing, and deployment workflows.

Contact

Pinned Loading

  1. nextjs-langchain-ai-chatbot nextjs-langchain-ai-chatbot Public

    A modern AI chatbot built with Next.js 15, LangChain, and Supabase featuring real-time streaming, RAG capabilities, multi-provider AI support, and comprehensive chat management.

    TypeScript

  2. ai-resume-matcher ai-resume-matcher Public

    AI Resume Matcher is a full-stack app that uses AI (Google Gemini) to parse PDF resumes, extract structured data, and compare them to job descriptions—returning match scores and gap analyses.

    JavaScript

  3. receipt-ai-expense-tracker receipt-ai-expense-tracker Public

    Receipt AI Expense Tracker is a web app that lets users upload images of receipts. The system uses AI (Google Gemini) to extract structured expense data (merchant, date, items, amounts), auto-categ…

    TypeScript 1 1

  4. AI-Product-Listing-Assistant AI-Product-Listing-Assistant Public

    AI Product Listing Assistant is an intelligent e-commerce tool that takes a product image as input and uses AI (Google Gemini) to auto-generate a product title, description, and relevant tags—avail…

    HTML

  5. customer-support-on-twitter customer-support-on-twitter Public

    A full-stack, AI-powered customer support assistant for Twitter / support tickets, capable of interpreting both text and images and producing smart replies in real time.

    HTML