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

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Block or report eauchs

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
eauchs/README.md

Théophile Lafargue | AI Infrastructure & MLOps 🚀

I build resilient, high-performance AI systems that bridge the gap between datacenter-scale reasoning and edge-constrained reality. Currently a Student-Entrepreneur at Paris-Saclay (Pépite PEIPS) and an invited attendee at OpenAI DevDays.

🏆 Key Achievements

  • Patent Holder (FR2511116): Invented a hybrid RAG architecture for stateful AI communication over low-bandwidth networks (2G/SMS).
  • StepFun Contributor: Engineered a local deployment architecture for Step-3.5-flash on Apple Silicon (PR #14 merged in official cookbook).
  • Amundi R&D: Architected "Alpha Narratif," a full-stack market simulator modeling narrative warfare in quantitative finance.

🛠️ The R&D Stack

  • Infrastructure: Bare-metal Homelab (Arch Linux, AMD ROCm), Apple Silicon (MLX), Edge IoT (Raspberry Pi).
  • AI/ML: Distributed Inference, Diffusion LLMs (dLLMs), RAG pipelines (ChromaDB, SmolDocling).
  • Engineering: Python (Asyncio), C++, React/TypeScript, MLOps (Docker, Netdata).

📂 Featured Projects

Project Concept Tech
Patent-Low-Bandwidth Stateful AI over 2G/SMS Python, RAG, ChromaDB
Step-3.5-Flash Local Agentic Sandbox (PR #14) Apple Silicon, MLX
Speech-Pipeline Real-time S2S with Barge-in MLX, Python, Latency-Optimized
Enigma-Shell Natural Language VM Control JavaScript, v86, Local LLMs

📬 Connect with me

Pinned Loading

  1. enigma-shell enigma-shell Public

    An experimental web shell to control a full Linux OS (v86) with natural language via local LLMs.

    JavaScript 3

  2. speech-to-speech-pipeline speech-to-speech-pipeline Public

    A real-time, interruptible (barge-in) conversational AI pipeline (STT-LLM-TTS) running locally. Optimized for Apple Silicon (MLX).

    Python 2

  3. gui-agent gui-agent Public

    A two-layer GUI agent for macOS. A VLM (Vision Language Model) handles perception, while a separate LLM (Qwen) manages high-level strategy and decision-making. Built with Python, OpenAI API, and Py…

    Python 1

  4. patent-low-bandwidth-ai patent-low-bandwidth-ai Public

    Backend for my 'Stateful AI over Low-Bandwidth Networks' patent (FR2511116). A hybrid RAG pipeline (SmolDocling, ChromaDB, Reranker) with SMS support, separating local VLM (perception) from the mai…

    Python 1