Skip to content
View DevDizzle's full-sized avatar
🎯
Focusing
🎯
Focusing
2 followers · 13 following

Achievements

Achievement: YOLOAchievement: Pull Sharkx2

Achievements

Achievement: YOLOAchievement: Pull Sharkx2

Block or report DevDizzle

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 supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
DevDizzle/README.md

Evan Parra 👋

ML Engineer | Building Production AI Systems on GCP

I build end-to-end ML systems that ship to production. My focus is autonomous pipelines, MLOps, and LLM-powered applications on Google Cloud Platform.

MS in Artificial Intelligence (FAU, 2025) | Google Certified ML Engineer

🔧 What I Build

Area Focus
ML Pipelines End-to-end data ingestion → feature engineering → model deployment
LLM Applications RAG systems, prompt chaining, MCP tool servers
MLOps CI/CD for ML, model versioning, monitoring, cost optimization
Data Engineering BigQuery, ETL/ELT pipelines, real-time processing

🚀 Production Systems

Financial ML Platform

Autonomous trading signal system processing ~10GB daily market data. Full MLOps lifecycle from ingestion to deployment.

  • LLM-augmented ETL with prompt chaining
  • MCP server for AI agent tool-calling
  • CI/CD: GitHub Actions → Cloud Build → Cloud Run
  • 50% inference cost reduction via dynamic model routing

Stack: Python, BigQuery, Vertex AI, Cloud Run, Pub/Sub, MCP

MCP Financial Tools Server

Model Context Protocol server enabling AI agents to query real-time financial data. Production-deployed on Cloud Run with SSE transport.

Stack: Python, FastMCP, BigQuery, Cloud Run

📂 Selected Projects

Autonomous Invoice Agent

Multi-agent system automating invoice lifecycle: Ingestion → Validation → Approval → Payment. Self-correction loops for data extraction.

Stack: Python, LangGraph, xAI Grok, FastAPI, Cloud Run

Serverless PII Vault

Secure file storage with user isolation and irreversible PII redaction using event-driven architecture.

Stack: Cloud Run, Cloud DLP, Vertex AI, FastAPI

RAG Paper Analyzer

Multi-document scientific paper Q&A with citation tracking. Vertex AI Vector Search + Gemini.

Stack: RAG, Vertex AI, Gemini, FastAPI, Firestore

YOLOv9 Detection Guide

End-to-end guide for fine-tuning YOLOv9 on custom datasets.

Stack: PyTorch, YOLO, Computer Vision

💻 Tech Stack

ML/AI:       Vertex AI, Gemini, TensorFlow, PyTorch, Scikit-Learn
Cloud:       GCP (BigQuery, Cloud Run, Pub/Sub, Cloud Functions)
MLOps:       GitHub Actions, Cloud Build, Docker, Model Registry
Data:        Python, SQL, Pandas, dbt, Airflow
Backend:     FastAPI, Python, Node.js
Frontend:    Next.js, React, TypeScript

📜 Certifications

  • Google Professional Machine Learning Engineer (2025)
  • Google Advanced Data Analytics Certificate
  • MS Artificial Intelligence — Florida Atlantic University

📫 Connect

Currently open to ML Engineer and Data Engineer opportunities. Remote or US-based.

Popular repositories Loading

  1. gammarips-engine gammarips-engine Public

    An end-to-end, serverless AI platform built on Google Cloud that automatically ingests and analyzes financial data to generate actionable trading signals for the Russell 1000. This repository conta…

    Python 6 1

  2. prompt-engineering prompt-engineering Public

    An iterative pipeline for optimizing prompt engineering strategies to generate high-quality structured requirements documents. Uses Dynamic Adaptive Prompt Optimization (DAPO) and an LLM-as-a-Judge…

    Python 4 1

  3. yolov9-object-detection-guide yolov9-object-detection-guide Public

    Fine-tune YOLOv9 for custom object detection with this step-by-step guide, including dataset preparation, training, validation, and inference tools.

    Jupyter Notebook 2

  4. linear-programing-assest-allocation linear-programing-assest-allocation Public

    This notebook performs portfolio optimization for a selection of Exchange-Traded Funds (ETFs) with the goal of minimizing investment risk while ensuring a minimum annual return.

    Jupyter Notebook 1

  5. travel-bloom travel-bloom Public

    A simple, dynamic travel recommendation website showcasing destinations with search functionality and visually engaging content.

    HTML

  6. node-pruning-research node-pruning-research Public

    Project exploring the impact of node pruning on CNN performance metrics within a stratified k-fold cross-validation framework. Focuses on optimizing recall for medical imaging tasks while analyzing…

    Jupyter Notebook