Skip to content
View josephfayyaz's full-sized avatar

Block or report josephfayyaz

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
josephfayyaz/README.md

Yousef Fayyaz

AI/ML builder focused on NLP, multimodal computer vision, and reinforcement learning

Followers Public Repositories Location

Professional Summary

I build research-driven machine learning systems from problem framing to reproducible training and evaluation.

My recent work spans:

  • Sarcasm and sentiment detection across English varieties
  • Multimodal wildfire burned-area prediction from pre-fire signals
  • Reinforcement learning for robust locomotion with domain randomization
  • Human-centered product prototyping (Vue 3 + Pinia)

I am open to AI/ML engineering roles, research internships, and applied ML collaborations.

Featured Projects

Project What I Built Core Stack
sarcasm-detection-nlp Unified training/inference pipelines for sarcasm and sentiment classification using encoder and decoder baselines, plus custom heads and variety-aware tuning. Python, Hugging Face Transformers, RoBERTa, DistilBERT, Mistral + QLoRA
WildFire Comparative multimodal deep learning framework to predict final burned area using pre-fire satellite, terrain, weather, and infrastructure data. Python, PyTorch, geospatial data workflows
RL Custom MuJoCo Hopper research with PPO, curriculum/domain randomization, and entropy scheduling for robust policy learning. Python, MuJoCo, Stable-Baselines3, RL evaluation tooling
Focus_Bloom Study-focus application prototype for HCI with session setup, timer flow, invite logic, and private/public modes. Vue 3, Pinia, JavaScript, Tailwind CSS

Additional Repositories

What Recruiters Usually Ask Me About

  • End-to-end ML experimentation (data handling, training loops, evaluation, error analysis)
  • Model robustness across domain shifts and dataset variations
  • Building readable, modular repo structures for team handoff
  • Translating research ideas into practical implementation

Technical Toolkit

Python PyTorch Transformers LoRA/QLoRA NLP Computer Vision Reinforcement Learning MuJoCo Jupyter Vue 3 Pinia Tailwind CSS Git

GitHub Snapshot

GitHub stats Top languages

Contact

  • GitHub: @josephfayyaz
  • Location: Italy
  • Opportunities: AI/ML internship, junior ML engineer, research assistant roles

If you are hiring for AI/ML work, start with the featured projects above to review my technical depth and implementation style.

Popular repositories Loading

  1. RL RL Public

    Python 5 1

  2. finance_coursera finance_coursera Public

    Jupyter Notebook 3

  3. WildFire WildFire Public

    Python 3

  4. sarcasm-detection-nlp sarcasm-detection-nlp Public

    Figurative Language AI Recognition

    Python 3 1

  5. Focus_Bloom Focus_Bloom Public

    Forked from parastoo-hashemi/Bloom_together

    An app for deep focusing during study (HCI course)

    Vue 3

  6. josephfayyaz josephfayyaz Public

    3