Omid Aghdaei

Angestellt, Data Scientist, Part AI Research Center
Tehran, Iran, Islamic Republic of

Skills

Speech recognition
Deep Learning
Computer Vision
Research
Data visualisation
Data Cleaning
Linux
PyTorch
Docker
SQL
TensorFlow
Deep learning
Python
Machine Learning
Data Science
Technology
Research and Development
Big Data
Deployment
Artificial intelligence
Mathematics
Computer Science
Git
GitLab
ML
Code
Statistics
Natural Language Processing
OpenCV
Python pandas
NumPy
Keras
scikit-learn
AWS
Artificial neural networks
Distillation
ONNX
Quantization
Pytorch
Microsoft SQL Server
Python programming
Deep Neural Networks (DNN)
Vim
Artificial Intelligence (AI)
Data Mining
Image Processing
Deep Reinforcement Learning
AirSim
Silero VAD
Reinforcement Learning
Webrtc VAD
Function Approximation
Intelligent Systems
Workflow of Machine Learning Projects
Data Visualization
AI terminology
AI Strategy
Human-level Performance (HLP)
Concept Drift
Model baseline
ML Deployment Challenges
Project Scoping and Design
MLOps
Unit Testing
Data Collection
Analytics
Statistical Analysis
Presentation skills
Team work
Decision Making
attention to detail

Timeline

Professional experience for Omid Aghdaei

  • Current 5 years and 3 months, since Mar 2021

    Data Scientist

    Part AI Research Center

    Played key role in developing & optimizing state-of-the-art models for audio-to-text conversion. Collaborated on project for converting telephone speech to text, leading to best-performing model in Iran. Contributed to Speaker Diarization projects, successfully identifying & separating speakers in audio recordings. Leveraged tools like VAD to improve speech segmentation. Utilized model compression techniques like ONNX, Distillation, and Quantization to optimize size, performance, and deployment efficiency.

  • 2 years and 10 months, Dec 2019 - Sep 2022

    Research Assistant

    Ferdowsi University of Mashhad

    Developed deep RL system for drone navigation, achieving 2% accuracy improvement and 18% faster inference. Utilized MiDaS algorithm for obstacle detection in diverse weather conditions. Trained ResNet-8 on real collision datasets for precise decision-making. Compressed networks with ONNX, resulting in 25% faster inference with minimal accuracy decrease. Developed specialized model with YOLO v5 for small obstacle detection, enhancing drone's navigation capabilities in complex environments.

Educational background for Omid Aghdaei

  • 3 years and 1 month, Sep 2019 - Sep 2022

    Artificial Intelligence

    Ferdowsi University of Mashhad

    Thesis title: Quadcopter Autonomous Navigation using Deep Reinforcement Learning Grade: 3.61/4.00 GPA

  • 4 years, Sep 2014 - Aug 2018

    Information Technology (IT)

    Islamic Azad University South Tehran Branch

    Thesis title: The relation of Internet of Things in smart city and smart car Grade: 3.31/4.00 GPA

Languages

  • English

    C1 (Fluent)

  • German

    B1-B2 (Good)

  • Persian

    C2 (Expert / native speaker)

XING – The jobs network

  • Over 1 million jobs

    Find just the right job for you on XING.

  • Job offers just for you

    Get found by employers and over 20,000 recruiters.

  • 21 million members

    Connect with new people and gather inspiration to boost your working life.

  • Free membership

    Basic membership is free, but the opportunities are priceless.

Browse over 21 million XING members