Skip to content
View lu-cattai's full-sized avatar
🏠
Working from home
🏠
Working from home
2 followers · 1 following

Block or report lu-cattai

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
lu-cattai/README.md

Hi there, I'm Luísa 👋

Software Engineer | AI Researcher | Master's Candidate at UNESP

I am a Computer Scientist focused on the intersection of High-Performance Computing and Generative AI. Currently, my work centers on the optimization of Large Language Model (LLM) inference, specifically regarding memory management and efficiency in resource-constrained environments.

🛠 Tech Stack & Expertise

  • Languages: Python (Advanced), JavaScript/TypeScript (ES6+), C++ (Performance-focused).
  • AI & Data: LLMs (Llama, OpenAI API), LangChain, RAG Pipelines, NLP, and Inference Optimization.
  • Frontend: React.js, Styled Components, Redux, and modern Web APIs.
  • Infrastructure: Linux, Git, and High-Performance Computing (HPC) environments.

🔬 Research & Projects

  • Master’s Thesis (In Progress): Optimizing LLM inference through advanced memory management strategies to enable high-quality AI in limited-resource hardware.
  • Scientific Publication: Analysis of the Effectiveness of Language Models in Code Optimization (ERAD-SP 2024).
  • Full-stack Development: Built a comprehensive web platform for scientific information democratization using React.js and Node.js.

Note: Most of my recent technical work is hosted in private repositories due to academic research agreements and ongoing R&D projects.

📫 How to reach me

"Bridging the gap between academic research and scalable software engineering."

Popular repositories Loading

  1. lu-cattai lu-cattai Public

  2. ai-agent-routing ai-agent-routing Public

    AI Agent challenge using Ollama and Python for Artefact.

    Python

  3. llm-engineering-essentials llm-engineering-essentials Public

    Technical lab for GenAI Efficiency: Bridging low-level systems (C++) with high-level AI agents to optimize inference and resource usage.

    Python

  4. advanced-rag-orchestrator advanced-rag-orchestrator Public

    Modular RAG (Retrieval-Augmented Generation) pipeline using Python, LangChain, and ChromaDB. Optimized for local LLM orchestration with Ollama (Phi-3/Llama-3).

    Python