AI/ML builder focused on NLP, multimodal computer vision, and reinforcement learning
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.
| 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 |
- finance_coursera: Financial analysis coursework in Jupyter Notebook
- jupyternotebookcoursera: Intro data science notebook practice
- test: Sandbox repository for quick checks
- 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
Python PyTorch Transformers LoRA/QLoRA NLP Computer Vision Reinforcement Learning MuJoCo Jupyter Vue 3 Pinia Tailwind CSS Git
- 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.