Skip to content
View HyegoJarllys's full-sized avatar

Block or report HyegoJarllys

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
HyegoJarllys/README.md

Hi, I'm Hyego Maia

AI Workflow Engineer | Agentic Systems & LLMOps

I design and build agentic workflows and AI-driven architectures that transform complex processes into autonomous, decision-making systems.

My work combines structured thinking, data engineering, and LLMOps to orchestrate intelligent agents, integrate tools and data, and create scalable workflows that execute tasks end-to-end with reliability and observability.

I focus on helping companies move from manual operations and fragmented systems to intelligent, automated workflows powered by LLMs and real-time data.


What I do

I design and implement systems that:

  • Orchestrate multi-agent workflows for complex task execution
  • Integrate LLMs with tools, APIs, and data sources (RAG-based systems)
  • Automate decision-making processes using structured reasoning
  • Build end-to-end AI workflows (from ingestion to action)
  • Implement LLMOps pipelines (evaluation, monitoring, prompt/version control)
  • Ensure observability, reliability, and cost efficiency in AI systems

Services I offer

  • AI Workflow & Agent orchestration
  • LLMOps implementation and optimization
  • RAG systems with structured data integration
  • Data pipeline automation (Airflow / Python)
  • Data platform architecture (BigQuery / PostgreSQL)
  • AI-powered automation for business processes

Focus Areas

  • Agentic AI & Workflow Orchestration
  • AI Systems Architecture
  • LLMOps (evaluation, monitoring, optimization)
  • RAG Systems & Tool-augmented LLMs
  • Data Engineering for AI systems
  • Observability, reliability, and production AI

Featured Projects

Automated Data Platform + AI DataOps Agent

Production-grade data platform with:

  • Medallion architecture (Bronze → Silver → Gold)
  • Airflow orchestration and dbt transformations
  • 300+ data quality tests
  • Power BI dashboards
  • OpenClaw: AI-powered agent that detects failures, reasons about root causes, and suggests corrective actions using RAG + LLMs

View repository →


LIZ – Agentic AI Assistant (RAG System)

AI assistant built with event-driven architecture that:

  • Uses structured knowledge and data pipelines
  • Performs context-aware reasoning
  • Executes responses based on real data and workflows

View repository →


Tech Stack

AI & Agents LLMs • RAG • LLMOps • LangChain • Agent orchestration

Data Python • SQL • dbt • Airflow

Cloud GCP • BigQuery • Cloud Run • Pub/Sub

Engineering Docker • APIs • Event-driven architecture • Distributed systems


About my approach

I build systems with a strong focus on:

  • Autonomy → workflows that execute without constant human input
  • Reliability → robust systems with monitoring and safeguards
  • Observability → visibility into AI decisions and pipeline behavior
  • Scalability → cloud-native, production-ready architectures
  • Structured reasoning → applying system thinking to AI workflows

Contact

Pinned Loading

  1. Automated-Data-Platform-Medallion-Architecture Automated-Data-Platform-Medallion-Architecture Public

    Production-grade GCP data platform with Medallion architecture, dbt, Airflow and OpenClaw (AI agent for autonomous incident response).

  2. ai-assistant-rag-liz ai-assistant-rag-liz Public

    Production-style RAG assistant for institutional use — strict document grounding, async analytics, IAM-aware architecture.

  3. data-analytics-fundamentals data-analytics-fundamentals Public

    Applied data analytics studies — Python, Pandas, SQL, REST APIs and customer segmentation (Pareto, RFM-style).

    Jupyter Notebook

  4. Building-with-the-Claude-API Building-with-the-Claude-API Public

    Hands-on portfolio from Anthropic's official Claude API course — agents, tool use, RAG, evaluations, MCP, prompt engineering.

    Jupyter Notebook