cv

Basics

Work

  • 2022.01 - 2023.01
    Data Scientist
    Tapsi
    Improved ETA service and enhanced spatial understanding using Graph Neural Networks.
    • GNNs for ETA Prediction
    • Seasonality-Aware Pre-processing
    • Location Matching Enhancement
  • 2021.01 - 2022.01
    Software Engineer
    Tapsi
    Owned Matching Service and optimized algorithms to enhance driver-passenger allocation.
    • Optimized Matching Algorithm
    • Enhancing Software Infrastructure

Volunteer

  • 2019.01 - 2021.01

    Tehran, Iran

    Scientific Committee Member
    Young Scholars Club (YSC)
    Lecturer and Examiner for IOAA & INOAA Team Selection.
    • Lecturer and Examiner
    • Team Selection for IOAA & INOAA

Education

  • 2019.01 - 2024.09

    Tehran, Iran

    B.Sc
    Sharif University of Technology
    Computer Engineering
    • Deep Learning
    • Machine Learning
    • Artificial Intelligence
    • Advanced Information Retrieval
    • Game Theory
    • Linear Algebra
  • 2018.01 - 2019.01

    Tehran, Iran

    Pre-University
    Young Scholars Club
    Astronomy & Astrophysics

Awards

Certificates

Publications

Skills

Data Science & Machine Learning
Luigi
MLflow
Metaflow
Prefect
PyTorch
Dassl
Hugging Face Transformers
RAPIDS
TensorFlow
Keras
PyTorch Geometric
Spark MLlib
Scikit-Learn
XGBoost
Catboost
PySpark
Pandas
Numpy
Matplotlib
Seaborn
Programming & Development
Python
Django
Nodejs
Java
Go
C++
C
R
LATEX
DBMS
Metabase
Grafana
Tableau
Power BI
MongoDB
PostgreSQL
Redis
Hazelcast
MySQL

Languages

Persian
Native speaker
English
Fluent

Projects

  • - Present
    Vision-Language Models Toolbox
    A Python library for fine-tuning and evaluation of vision-language models such as CLIP & BLIP with PyTorch, supporting various datasets and tasks like image classification.
  • - Present
    MedSegDiff: Medical Image Segmentation with Diffusion Model
    Implements the MedSegDiff: Medical Image Segmentation with Diffusion Probabilistic Model paper for medical image segmentation, using the LGG Segmentation Dataset to detect tumor and cancer anomalies.
  • - Present
    Bootstrap Your Own Latent (BYOL)
    A Pytorch implementation of BYOL using a pre-trained ResNet backbone on the STL10 dataset.
  • - Present
    Generative Models
    Experiments with VAEs, GANs, and DDPMs, on the Fashion MNIST dataset.
  • - Present
    Zero-shot Object Detection
    Zero-shot object detection with CLIP, utilizing Faster R-CNN for region proposals.
  • - Present
    Adversarial Robustness
    Evaluating robustness against adversarial attacks such as FGSM and PGD.
  • - Present
    Full-stack Food Delivery Platform
    A food delivery application built with a Python backend (FastAPI & Docker) and a Vue.js frontend. It presents an event-driven microservices architecture with many modern features!
  • - Present
    FastAPI JWT Authentication
    A scalable authentication middleware for FastAPI, employing Redis to provide efficient JWT-based authentication and seamless integration with distributed systems.
  • - Present
    Messaging & DBMS Libraries
    Python libraries for distributed event-driven architectures (rabbitmq-rpc) and streamlined database interactions and connectivity (mongo-motors, asyncpg-client, aredis-client).