Machine Learning Engineer

EbrahimGhafourzadeh

I develop deep learning and LLM-based systems, focusing on agentic AI and transforming research concepts into production-ready solutions.

About

Deep Learning, LLMs, and Agentic AI

I build intelligent language systems using large language models (LLMs), agentic AI, and embedding-based methods. My work focuses on retrieval-augmented generation (RAG), multi-agent systems, and scalable pipelines for tasks like semantic search and question answering.

  • Open source: Core contributor to Hazm, a widely used Persian NLP library.
  • Modeling: PyTorch, TensorFlow, LLMs, agentic AI, embeddings, and RAG systems.
  • Product thinking: Turning research ideas into scalable pipelines, APIs, and tools.

Featured Open Source Work

Hazm Library Contribution

I contributed to Hazm, an open-source Python library for Persian natural language processing, by adding model-driven modules, pretrained resources, and improvements that make the library easier to use across platforms.

Hazm Persian NLP library preview

Hazm 0.8

  • Implemented word embedding and sentence embedding modules.
  • Added pretrained FastText word embeddings and sentence embedding models.

Hazm 0.9

  • Improved Windows compatibility by moving from Wapiti to Python-crfsuite.
  • Added pretrained Chunker and POS tagger models.
  • Implemented embedding training workflows and an EmbedRank keyword extraction example.

Hazm 0.9.2

  • Added pretrained dependency parser models.
  • Improved project test coverage.
Rumour detection project preview

PyTorch / NLP

Rumour Detection

A PyTorch classification project for experimenting with rumour detection models, preprocessing options, and training configurations.

  • PyTorch
  • Classification
  • Experimentation
  • Transformers
  • Bert language models
  • Matplotlib
Persian POS tagger project preview

Persian NLP

Persian POS Tagger

A comparative implementation of Persian part-of-speech tagging with neural and classical approaches.

  • PyTorch
  • TensorFlow
  • CRF
  • spaCy
  • Numpy
  • Pandas
Book recommendation system preview

Recommendation

Book Recommendation System

A recommendation engine for a book donation platform using text embeddings, cosine similarity, and PCA.

  • Embeddings
  • Similarity
  • PCA
  • Recommendation System
  • Pandas
Persian keyword extraction project preview

Keyphrase Extraction

Persian EmbedRank

A Persian keyphrase extraction system adapted from the EmbedRank approach and integrated with Hazm-based models.

  • EmbedRank
  • Algorithm
  • Sentence Embeddings
Clothes recommendation system preview

Recommendation

Clothes Recommendation System

A preference-based recommendation system that represents user taste as vectors and matches items with similarity and clustering methods.

  • K-means++
  • Clustering
  • Vector store
  • Similarity Algorithm
  • Recommendation System
Persian AI-generated text detection preview

Dataset / Detection

Persian AI-Generated Text Detection

A dataset and model exploration project for detecting AI-generated Persian text.

  • NLP
  • Dataset
  • Agentic AI
  • large language models
  • Text Classification