Skip to content
View nerofinal012's full-sized avatar

Block or report nerofinal012

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
nerofinal012/README.md

Hey, I'm Vhinzy

I'm an AI Engineer & Data Scientist based in Manila, Philippines. I build production LLM applications, RAG pipelines, and ML systems — currently helping a US-based procurement platform ship AI search features to enterprise clients.

Right now I'm working on:

  • AI Search over enterprise contract data using Amazon Bedrock + Claude
  • Multi-tier query routing (fast-path → LLM router) for sub-2-second latency
  • Embedding sync pipelines between MySQL, S3, and Bedrock Knowledge Bases

Currently learning: agentic workflows, evaluation frameworks for RAG, and AWS ML Specialty cert.


Stack I work in

LLMs & GenAI — Anthropic Claude (Sonnet, Haiku) · OpenAI (GPT-4, embeddings) · Google Gemini · Azure OpenAI · prompt engineering · function calling · multi-agent orchestration

RAG & Vector Search — Amazon Bedrock Knowledge Bases · vector databases · semantic & hybrid search · Supabase pgvector · Pinecone / FAISS / Weaviate

Cloud — AWS (Bedrock, SageMaker, Lambda, S3, QuickSight) · Azure (OpenAI, Speech, Functions, Blob)

Backend & ML — Python · Django · FastAPI · MySQL · PyTorch · TensorFlow · scikit-learn · Docker

Frontend (integration level) — React · Next.js · Streamlit


Featured Projects

A new portfolio is in the works — these will be pinned and updated soon. In the meantime, happy to walk through any of them on a call.

ContractIQ (in progress) — RAG over a public contract corpus. Bedrock + Claude Sonnet, hybrid retrieval, evaluation suite. Live demo coming soon.

PollyGlot — context-aware translation app. React + OpenAI GPT API with multi-turn conversation memory and AI-feedback correction.

AI Voice Agent for Claims Validation — multi-agent system orchestrating Azure Speech Services, OpenAI GPT, and Azure Language Service across Speech-to-Text → NER → Validation → TTS response agents.

Movie Recommendation System — semantic search using OpenAI embeddings with Supabase pgvector for vector similarity over movie metadata.


Get in touch


Outside of work: open-source AI tinkering, IoT side-projects, mentoring junior devs, and the occasional DOTA 2 ranked match.

Popular repositories Loading

  1. datasciencecoursera datasciencecoursera Public

    For completion purposes.

  2. datasharing datasharing Public

    Forked from jtleek/datasharing

    The Leek group guide to data sharing

  3. skills-copilot-codespaces-vscode skills-copilot-codespaces-vscode Public

    My clone repository

  4. mslearn-challenge-project-create-mini-game-with-copilot mslearn-challenge-project-create-mini-game-with-copilot Public

    Forked from MicrosoftDocs/mslearn-challenge-project-create-mini-game-with-copilot

    Starter and Final code for the Challenge project: "Challenge project - Build a minigame console app with GitHub Copilot"

  5. skills-secure-code-game skills-secure-code-game Public

    My clone repository

    Python

  6. Cisco-Dataset-Training Cisco-Dataset-Training Public

    Jupyter Notebook