Skip to content
View taroserigano's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report taroserigano

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
taroserigano/README.md

Hi, I'm Taro Serigano πŸ‘‹

Typing SVG

About Me

I'm a Senior AI Engineer and AWS Certified Solutions Architect building production LLM applications β€” retrieval-augmented generation, multi-agent orchestration, and fine-tuned models β€” end to end, from the model layer to the shipped product.

  • πŸ€– Currently building agentic RAG systems β€” LangChain / LlamaIndex agents grounded in graph + vector retrieval (Neo4j, ChromaDB)
  • 🧠 Fine-tuning open + closed models (QLoRA on Ollama, OpenAI GPT fine-tuning) for domain-specific compliance and analysis tasks
  • πŸ—οΈ Designing full-stack AI products β€” FastAPI/Python backends, React/TypeScript frontends, deployed on AWS
  • πŸ”­ 2026 goals: deeper multi-agent orchestration, shipping Hermes Agent
  • ⚑ Fun fact: I love watching YouTube and playing guitar between training runs

AI / ML Stack

Claude OpenAI LangChain LlamaIndex RAG Agentic AI
XGBoost PyTorch Hugging Face QLoRA Neo4j ChromaDB

Full-Stack & Cloud

Skills


πŸš€ Featured Projects

Project What it does
MAG7 SEC Filings Analyzer Agentic RAG over SEC filings for the Magnificent 7 β€” FastAPI backend, multi-agent analysis
Agentic AI Travel Advisor Multi-agent travel planning system deployed on AWS
Policy Guardian RAG-powered LLM app for policy compliance Q&A
RAG Multi-Agent React App Multi-agent RAG pipeline surfaced through a React front end
GPT Compliance Fine-Tuning Fine-tuned OpenAI GPT model for compliance-domain analysis
Ollama QLoRA Fine-Tuning Local fine-tuning of open-weight models with QLoRA

Connect with me

LinkedIn Website

Profile views

Pinned Loading

  1. Agentic_AI_Travel_Advisor_Multi_Agents_Plumini_AWS Agentic_AI_Travel_Advisor_Multi_Agents_Plumini_AWS Public

    Python

  2. FINE-TUNING-Ollama-QLora______ FINE-TUNING-Ollama-QLora______ Public

    Python

  3. MAG-7-SEC-Filing-Analyzer-RAG-Agneitc-AI--FastAPI-App____ MAG-7-SEC-Filing-Analyzer-RAG-Agneitc-AI--FastAPI-App____ Public

    Python

  4. OPEN-AI-GPT-FINE_TUNING__Compliance_Model_2.1.2026---___ OPEN-AI-GPT-FINE_TUNING__Compliance_Model_2.1.2026---___ Public

    Python

  5. TweekySqueeky-FastAPI-Ecommer-App TweekySqueeky-FastAPI-Ecommer-App Public

    Python

  6. rentready rentready Public

    RentReady β€” AI-powered property management: XGBoost risk models, GraphRAG concierge, agentic chat across 6 surfaces

    Python