Skip to content
View cesaremcasa's full-sized avatar
3 followers · 2 following

Achievements

Achievement: QuickdrawAchievement: Pull Sharkx3Achievement: Pair Extraordinairex3Achievement: YOLO

Achievements

Achievement: QuickdrawAchievement: Pull Sharkx3Achievement: Pair Extraordinairex3Achievement: YOLO

Block or report cesaremcasa

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
cesaremcasa/README.md

Cesar Augusto

AI Systems Engineer. Agentic AI and autonomous orchestration systems. Not demos, real systems.

⚡ Tech Stack

Python FastAPI RAG FAISS LangChain Google Cloud Azure LLM Logging Architecture

Engineering Focus

I architect and deploy AI systems with emphasis on:

Agentic AI & LLM Systems:

  • Autonomous and multi-agent systems
  • RAG (Retrieval-Augmented Generation) architecture
  • LLM orchestration and tool calling
  • Prompt engineering and transformer architectures
  • LangChain agents, chains, and tool integration
  • Model Context Protocol (MCP)
  • Vector search (Pinecone, AlloyDB Vector)

Cloud Platforms & MLOps:

  • Google Cloud Platform: Compute Engine, Cloud Run, AlloyDB, BigQuery, Gemini Ecosystem
  • Azure Machine Learning: Model deployment, endpoints, ML workflow operations
  • Serverless pipelines and infrastructure automation
  • VPC, IAM, and cloud security patterns

Data & Analytics Engineering:

  • DuckDB analytics and BigQuery optimization
  • ETL pipelines and data ingestion
  • Structured and unstructured data processing
  • REST APIs, OAuth, and webhook integrations
  • MCP Toolbox for database orchestration

Backend Development & Automation:

  • Python (production-grade), Node.js, TypeScript
  • FastAPI and automation frameworks
  • Backend integration and CI/CD pipelines
  • Cron orchestration and scheduled workflows
  • Structured logging and observability

Certifications

Google Cloud:

  • Gen AI Leader
  • Gen AI Agents: Transform Your Organization
  • Transformer Models & BERT Model
  • Attention Mechanism
  • Build AI Agents with Enterprise Databases

IBM:

  • Build RAG Applications: Get Started
  • Develop Generative AI Applications: Get Started
  • Generative AI: Introduction & Applications

Vanderbilt University:

  • Model Context Protocol for Leaders: Generative AI Agents
  • Agentic AI and AI Agents: A Primer for Leaders
  • Prompt Engineering for ChatGPT

University of Colorado Boulder:

  • Modern AI Models for Vision and Multimodal Understanding

Duke University:

  • Python Essentials for MLOps

Whizlabs:

  • Azure ML: Deploying, Managing & Experimenting with Models

Education

Bachelor of Computer Science. Universidade Virtual do Estado de São Paulo (UNIVESP), 2018

Bachelor of Advertising and Marketing. Pontifícia Universidade Católica de São Paulo (PUC-SP), 2014

Languages

Portuguese (Native) • English (Fluent) • Spanish (Advanced) • French (Advanced)

Connect

Location: Winter Garden, Florida | Open to relocation

Email: cesardonahill3@gmail.com

LinkedIn: cesar-augusto

Philosophy: I focus on clarity, grounded engineering, and reproducible pipelines. Real-time RAG infrastructures, multi-step reasoning systems, and measurable ROI through autonomous orchestration.

Pinned Loading

  1. Compliance-Guard Compliance-Guard Public

    An automated NIST cybersecurity compliance analyzer using fine-tuned Mistral-7B with LoRA adapters and production-grade infrastructure. Implements 4-bit quantization reducing VRAM from 15GB to 5GB,…

    Python 1

  2. My-Orlando-Experience My-Orlando-Experience Public

    A production-grade Retrieval-Augmented Generation backend for Orlando theme park visitor assistance with decoupled architecture preventing context contamination. Implements FastAPI service layer, F…

    Python 1

  3. Real-Time-Fraud-Detection-with-Deep-Learning Real-Time-Fraud-Detection-with-Deep-Learning Public

    Streaming anomaly detection on taxi trip data. FastAPI producer, Redpanda, and a GPU worker running a trained autoencoder. Unsupervised, with the decision threshold derived from validation error.

    Python 1

  4. delta-one-architecture delta-one-architecture Public

    Delta One. A voice first Android environment built around intention, on AOSP. Architecture and design record. Models propose, deterministic code authorizes. Part of Mycellium Lab.

  5. hyperion-architecture hyperion-architecture Public

    Compound urban flood nowcasting for the next six hours. Method and architecture record. Calibration over accuracy, leakage inspection on every run. Part of Mycellium Lab.

  6. manager-architecture manager-architecture Public

    Operations intelligence for independent restaurants. Architecture and design record. Code calculates, the model narrates. Part of Mycellium Lab.