Skip to content
View pandego's full-sized avatar
🤓
Crushing code like it's a piñata 🎉💻🔨
🤓
Crushing code like it's a piñata 🎉💻🔨
25 followers · 8 following

Achievements

Achievement: Pull Sharkx3Achievement: Pair Extraordinairex3Achievement: YOLOAchievement: Quickdraw

Achievements

Achievement: Pull Sharkx3Achievement: Pair Extraordinairex3Achievement: YOLOAchievement: Quickdraw

Block or report pandego

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
pandego/README.md

Hi, I'm Miguel 👋🏼 and I build AI systems!

I'm a Data Scientist and certified AI Engineer with 10+ years building AI systems for startups and enterprise teams.

  • What I build: LLM applications like copilots, RAG systems, and multi-agent workflows
  • Industries: Automotive, Manufacturing, AgriTech, and MedTech
  • Focus: Production-ready AI systems that work under real-world pressure

Let's connect on LinkedIn or check out some of my work below.

🎯 Recent Case Studies

  • Automated Patent Trend Intelligence with multi-LLM workflow sliced diligence time by ~90% → here
  • On-prem AI chatbot for 300+ employees, keeping data sovereign while cutting onboarding time by ~70% → here
  • AI Agent for SQL-Based Data Retrieval and Exploratory Data Analysis → here
  • Customer Care Automation with multi-Agent workflow → here
  • Plant-wide ergonomics assessment time reduced from 12 months to 3 weeks with 3D pose-estimation → here

🛠️ Tech Stack

My tech stack combines modern AI with production-proven tools:

  • LLMs: OpenAI, Anthropic Claude, Google Gemini, Groq, Qwen
  • AI Agent Orchestration: LangChain, LangGraph, PyDanticAI
  • Vector Database: PostgreSQL (pgvector), Supabase, Pinecone, Qdrant
  • Monitoring & Evals: Custom observability pipelines, LangSmith, LangFuse, Arize Phoenix, GuardrailsAI
  • Data/Infrastructure: Python, Docker, FastAPI, REST, MCP, GitHub Actions, Pydantic, CI/CD, Azure, Databricks
  • Machine Learning: Scikit-learn, Pandas, NumPy, XGBoost, PyCaret, PyTorch/Lightning
  • Specialties: Context Engineering, RAG & Vision-RAG Systems, Multi-Agent Workflows

🧩 OSS Contributor Activity (auto-updated)

Projects contributed to:

Latest merged PRs:

Last updated: 2026-05-22 07:32 UTC

🔐 About Private Work

Most deliverables live inside private repositories, client-controlled GitHub orgs or air-gapped infrastructure covered by NDAs. The public projects you see highlight OSS contributions, reproducible studies, and playgrounds where I battle-test new frameworks before hardening them for secure production rollouts.

🤝 Want to Work Together?

Hire me on Upwork or book a call to discuss your project.

Hire me on Upwork   Book an intro call   Follow on LinkedIn

Pinned Loading

  1. patent-trend-analysis-using-llm patent-trend-analysis-using-llm Public

    End-to-end AI pipeline for classifying, translating, clustering, and summarizing patent filings to surface EV-battery technology trends for IP and innovation teams.

  2. secure-entreprise-ai-assistant secure-entreprise-ai-assistant Public

    Confidential ChatGPT-like assistant with RAG, translation, and secure on-premises deployment for 300+ employees.

  3. ai-powered-ergonomic-assessment-with-3d-skeleton-tracking ai-powered-ergonomic-assessment-with-3d-skeleton-tracking Public

    Automated ergonomic scoring from depth-video, cutting plant-wide studies from 12 months to 3 weeks.

  4. mlflow-postgres-minio mlflow-postgres-minio Public

    Automatic setup and deploy a MLflow server.

    Python 1

  5. mdn-playground mdn-playground Public

    A playground for Mixture Density Networks.

    HTML 5

  6. testimonials testimonials Public

    This repo collects recommendations and feedback from **founders, C-levels, managers, colleagues, and clients** I’ve worked with while building AI systems.