AI Engineer

Expertise in developing advanced NLP, speech and computer vision models, fine-tuning LLMs, and deploying scalable backend systems. Proven track record of delivering innovative solutions to complex challenges in data processing and AI applications.

Tehran | +989213207541 | razitmazinani@gmail.com | LinkedIn: razi-taj-mazinani | GitHub: razi-tm

Skills

Deep Learning - Machine Learning

• PyTorch, TensorFlow, Keras, Fastai, LAVIS, YOLO, Scikit-Learn, OpenCV

Data Analytics

• Numpy, Pandas, Matplotlib

Hardware Assembly and Configuration

• Assembling machine learning stations

Other

• Linux, Git, Docker, Django, ElasticSearch, FAISS, PostgreSQL, Pgvector

English

• Professional efficiency

Work Experience

• Backend Developer at NetBox
• AI Engineer at Sharif Search
• AI Engineer (Internship) at Sharif Search

Soft Skills

• Problem-solving and critical thinking
• Communication and collaboration in cross-functional teams
• Time management and prioritization
• Creative thinking and innovation
• Adaptability and resilience in fast-paced environments
• Attention to detail and quality assurance
• Interpersonal skills for stakeholder engagement
• Curiosity and continuous learning

Projects

Building a Very Large Persian Dataset for Fine-Tuning LLMs

• A massive Persian dataset in question-answering format, including 50k samples and around 200k lines, tailored for NLP tasks.

Fine-Tuning a Large Language Model

• Fine-tuned Llama 3 using the dataset mentioned above. Enabled the model to understand and generate Persian text, overcoming its limitations for handling the Persian language.

Retrieval Augmented Generation (RAG)

• Developed a system that combines information retrieval and generative AI to improve the accuracy and relevance of generated text by leveraging external datasets.

Speech-to-Text

• Implemented a robust pipeline for converting spoken language to written text with high accuracy, optimized for noisy environments.

Speaker Identification

• Designed and deployed a deep learning-based system to identify and distinguish speakers.

Open-Source Contributor (Pyannote.Audio)

Image Similarity Search

• Developed a fast and scalable image similarity search engine using embeddings.

Face Recognition with Increased Speed Using a Creative Method

• Innovated on traditional algorithms to accelerate face recognition tasks while maintaining high accuracy, optimized for large-scale datasets.

Customized Scraper for a Specific Website

Handling Big Data Using PostgreSQL

• Implemented data management strategies utilizing PostgreSQL to efficiently store, query, and analyze large datasets. Leveraged its advanced features, like indexing, to optimize performance and ensure scalability in data processing.

Deployment: Dockerized and deployed projects for production, ensuring scalability, reliability, and ease of integration when required.