Skip to content
View KenJend0's full-sized avatar
6 followers · 4 following

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Block or report KenJend0

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
KenJend0/README.md

Aissi Teyssir — Machine Learning Engineer

Engineering student (ESILV, Data & AI) and Master's student (DataScale, Université Paris-Saclay), building applied ML systems end to end — from model design to the pipelines and product surfaces that put them in front of users.

Currently a research intern at the University of Science and Technology of Hanoi, working on lightweight computer vision models for 3D fragment reassembly.

Interested in: applied ML systems, computer vision, recommender systems, and the engineering discipline behind reliable ML in production.

Highlighted projects

  • Sillon — social music discovery platform (Next.js, Expo, Supabase) with a batch collaborative-filtering recommendation pipeline.
  • Lightweight Fracture Segmentation CNN — 544K-parameter multi-view CNN for 3D fracture segmentation, 15-step ablation study (68.1% → 96.7% F1), ~23× smaller than a PTv3/GARF-mini baseline.
  • Safran Tech — deep learning pipelines for radiographic image transformation (DAIN / FILM / RIFE) supporting automated turbine blade inspection.

Tech stack: Python · PyTorch · TensorFlow · scikit-learn · SQL · PostgreSQL · Supabase · Git / GitHub Actions

LinkedIn · Sillon · aissiteyssir16@gmail.com

Pinned Loading

  1. lightweight-fracture-segmentation-cnn lightweight-fracture-segmentation-cnn Public

    Engineering showcase: 544K-param multi-view CNN for 3D fracture segmentation (15-step ablation, 68.1%->96.7% F1, 23x smaller than PTv3/GARF-mini baseline)

  2. rag_mobile rag_mobile Public

    Mobile Retrieval-Augmented Generation app — on-device retrieval + LLM Q&A (Kotlin).

    Kotlin 1

  3. Projet_indexation Projet_indexation Public

    Football match data pipeline: Kafka, Logstash, Elasticsearch and PySpark over ~1900 matches from 5 European leagues.

    Python

  4. qa-project qa-project Public

    Fine-tuned BERT/DistilBERT/RoBERTa for extractive QA on SQuAD, with a FastAPI + Streamlit demo.

    Jupyter Notebook