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

Achievements

Achievement: QuickdrawAchievement: Starstruckx2Achievement: YOLOAchievement: Pull Sharkx2

Achievements

Achievement: QuickdrawAchievement: Starstruckx2Achievement: YOLOAchievement: Pull Sharkx2

Block or report cristianleoo

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
cristianleoo/README.md

Cristian Leo

Typing intro

Portfolio LinkedIn Medium Email

> boot profile --user cristianleoo

role.current        = "Data Scientist @ AWS"
focus.01            = "secure agentic systems"
focus.02            = "LLM behavior + interpretability"
focus.03            = "AI infrastructure that survives contact with reality"
writing.channel     = "medium.com/@cristianleo120"
open_source.mode    = "research-heavy, implementation-first"

System Snapshot

Now

  • Building AI systems where security is part of the design, not an afterthought.

  • Working on LLM-powered workflows, model behavior, and production-facing reliability.

  • Writing about architecture shifts, model internals, and cybersecurity knowledge in language models.

Domains

  • LLMs

  • AI security

  • Agentic systems

  • Interpretability

  • Retrieval-augmented generation

  • Applied ML engineering

Stack

Python TypeScript C++ PyTorch AWS Docker RAG LLMs Security

Selected Projects

Project What it is
models-from-scratch-python Rebuilding core ML models from scratch with Python and NumPy.
rag-knowledge-graph RAG pipelines with knowledge-graph-backed retrieval.
InfluencerPy CLI automation for social and workflow orchestration.
montecarlo-portfolio-management Quant finance experiments focused on Monte Carlo risk analysis.
Reinforcement-Learning RL implementations and environment experiments.

Latest Writing

Live Telemetry

GitHub stats Top languages
GitHub streak

Contact Surface

If you're building in AI infra, model behavior, security, or research-heavy product work, reach out.

Popular repositories Loading

  1. models-from-scratch-python models-from-scratch-python Public

    Repo where I recreate some popular machine learning models from scratch in Python

    Jupyter Notebook 129 41

  2. rag-knowledge-graph rag-knowledge-graph Public

    HTML 36 9

  3. montecarlo-portfolio-management montecarlo-portfolio-management Public

    Portfolio Management with Monte Carlo Simulation

    Python 22 8

  4. InfluencerPy InfluencerPy Public

    CLI Application to automate social media

    Python 16

  5. Reinforcement-Learning Reinforcement-Learning Public

    Jupyter Notebook 10 2

  6. gradient-flow-optimizer-neural-networks gradient-flow-optimizer-neural-networks Public

    This package provides an interactive Streamlit app to visualize the gradient flow of a simple neural network during training. You can adjust the network's parameters and see real-time updates of th…

    Python 4 2