Skip to content
View Max-Ghadri's full-sized avatar
😁
😁
12 followers · 17 following

Achievements

Achievement: Pair ExtraordinaireAchievement: QuickdrawAchievement: YOLOAchievement: Pull Sharkx2

Achievements

Achievement: Pair ExtraordinaireAchievement: QuickdrawAchievement: YOLOAchievement: Pull Sharkx2

Organizations

@SaveBirds-app @Second-Harmonic-Generation

Block or report Max-Ghadri

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
max-ghadri/README.md

Hi — I’m Max Ghadri, M.Sc.     Linkedin Google Scholar

AI Scientist

AI Scientist and ML Engineer focused on production GenAI, agentic RAG systems, and end-to-end ML/DL pipelines.

I fine-tune domain-specific SLMs, build LangGraph agent workflows with Knowledge Graphs and vector retrieval, and ship scalable APIs with FastAPI, Docker, and MLflow—from research prototypes to production-ready systems in healthcare and tech.

What you'll find here

  1. RAG Implementation Production-style RAG pipelines for document indexing into Qdrant and retrieval benchmarking with dense, BM25, and hybrid search.
  2. Non Question Proficiency Evaluation Knowledge Tracing models (SAINT+, LBKT, AKT) for estimating learner proficiency from video, reading, and interactive engagement signals.
  3. Second Harmonic Generation Open-source Fortran toolkits for thermal effects, phase mismatch, and coupled field modeling in nonlinear optics (FDM-based).
  4. SaveBirds.app Open-source bird atlases for North American species, generated from Breeding Bird Survey (BBS) data.

More public repos on SLM fine-tuning, Agentic AI, Knowledge Graphs, and other production AI projects are coming soon.

Pinned Loading

  1. RAG-Implementation/rag-retrieval-benchmark RAG-Implementation/rag-retrieval-benchmark Public

    Production-style benchmark for RAG retrieval: dense, BM25, hybrid, RRF, metadata filters & query rewriting on BEIR SciFact. Docker, Qdrant, FastAPI, GPU embeddings.

    Jupyter Notebook

  2. non-question-proficiency-evaluation/Video-Proficiency-SAINT_Plus non-question-proficiency-evaluation/Video-Proficiency-SAINT_Plus Public

    PyTorch implementation of SAINT+ for Transformer-based knowledge tracing and student performance prediction using time-aware educational interaction features.

    Python

  3. RAG-Implementation/rag-data-indexing-service RAG-Implementation/rag-data-indexing-service Public

    Production-style RAG data indexing pipeline: load, clean, chunk, embed, and index documents into Qdrant using Python, FastAPI, and sentence-transformers.

    Jupyter Notebook

  4. non-question-proficiency-evaluation/Interactive-Proficiency-AKT non-question-proficiency-evaluation/Interactive-Proficiency-AKT Public

    PyTorch implementation of Attentive Knowledge Tracing for student performance prediction with AKT-PID and AKT-CID model variants.

    Python

  5. Fortran-for-Science Fortran-for-Science Public

    Hands-on Fortran tutorial for science: installation, workflow, clean templates, and runnable examples for variables, I/O, loops, branches, arrays (ifort).

    Fortran

  6. Time-Series-Analysis Time-Series-Analysis Public

    Exploring the realm of Time Series Analysis through diverse forecasting and trend detection projects.

    Jupyter Notebook 1