Nour is currently unavailable
Nour Helal
Verified Expert in Engineering
Machine Learning Engineer and Developer
Cairo, Cairo Governorate, Egypt
Toptal member since July 12, 2023
Bio
Nour is a skilled professional focused on artificial intelligence. He has three years of experience leading development teams and seven years of experience designing and developing machine learning models and computer vision algorithms. He has also focused on computer vision to help autonomous cars and drones in environment inception and decision-making steps. Nour has applied AI to military applications, surveillance systems, optical character recognition, drones, and self-driven cars.
Portfolio
Fotopia
Research, Machine Learning Operations (MLOps), Team Management
Fotopia
Tesseract, EasyOCR, OpenCV, PyTorch, Azure Cloud Services, Image Analytics...
Egyptian Armed Forces Research Authority
Digital Imaging, Deep Learning, Computer Vision...
Experience
- Python - 10 years
- OpenCV - 8 years
- Deep Learning - 8 years
- C++ - 7 years
- Computer Vision - 6 years
- PyTorch - 5 years
- Team Management - 3 years
- Machine Learning Operations (MLOps) - 1 year
Work Experience
Machine Learning Team Lead
2023 - PRESENT
Fotopia
- Led the machine learning team to empower our stack of five products with artificial intelligence.
- Managed the research and development team to develop our new Arabic OCR model and document classifier.
- Handled the internship program curriculum and road map.
- Taught advanced deep learning and computer vision modules in our team training program.
Technologies: Research, Machine Learning Operations (MLOps), Team Management
Senior Machine Learning Engineer
2022 - 2023
Fotopia
- Developed an Arabic OCR-based product from scratch that the user can train to recognize specific documents.
- Built a product that can detect documents in images, classify document types, fix transformation defects, fix zone positions, retrieve textual data, perform post-processing and OCR post-correction, and export retrieved data to other platforms.
- Mentored junior developers to empower their knowledge in the field of AI.
Technologies: Tesseract, EasyOCR, OpenCV, PyTorch, Azure Cloud Services, Image Analytics, Image Analysis, Image Processing, Convolutional Neural Networks (CNNs), Deep Learning
Mid-senior Computer Vision Engineer
2021 - 2022
Egyptian Armed Forces Research Authority
- Developed an Arabic OCR system to digitize legacy paperwork for the Egyptian Ministry of Defense.
- Built a product to automate the new soldiers' registration and enrollment process via OCR-ing national ID cards.
- Designed and implemented multiple computer vision algorithms and deep learning techniques to improve military surveillance systems.
Technologies: Digital Imaging, Deep Learning, Computer Vision, Convolutional Neural Networks (CNNs)
Machine Learning Team Lead
2021 - 2022
iSoft Land, Inc.
- Designed a smart ecosystem to build, train, validate, and deploy machine learning algorithms and deep learning models that control aerial vehicles.
- Led a team of robotics and deep learning engineers to make a drone fly autonomously within urban environments.
- Managed a team of robotics and deep learning engineers through specific complex processes related to making a drone fly within urban environments.
Technologies: Team Management
Mid-senior Computer Vision Engineer
2020 - 2021
iSoft Land, Inc.
- Developed cutting-edge computer vision algorithms that enabled a drone to find the optimal, free takeoff point using an up-facing depth camera.
- Built a system for the drone to find the optimal landing point underneath using a deep learning depth estimation model.
- Collaborated with the robotics team to help in solving sensor fusion-related problems.
Technologies: Computer Vision, Robotics, Digital Imaging, Image Analytics, Image Analysis, Convolutional Neural Networks (CNNs), Deep Learning
Machine Learning Engineer
2019 - 2020
iSoft Land, Inc.
- Developed algorithms to control a drone and connect it to a simulation that teaches school students about drone development.
- Collaborated with the robotics team to solve various sensor-related problems.
- Made test fields to test the performance of the drones.
Technologies: Computer Vision, Robotics, Simulations, Convolutional Neural Networks (CNNs)
Deep Learning Engineer
2017 - 2019
Phoenix Team
- Made a level-three self-driving car for Ain Shams University. It can navigate safely within the campus to help people with special needs.
- Developed a deep reinforcement learning model from the PPO2 algorithm to control the vehicle.
- Trained the model using multiple agents on the cloud. A single front-facing RGB camera was the only source feeding this model with additional segmentation and feature extraction models to help with scene understanding.
Technologies: Deep Reinforcement Learning, Computer Vision, Robotics, Cloud, Image Processing, Convolutional Neural Networks (CNNs), Deep Learning
Machine Learning Engineer
2016 - 2017
Freelance
- Applied machine learning to vision systems in self-driven cars.
- Performed multiple projects related to facial recognition.
- Conducted investigations and worked on various projects related to object detection and recognition.
Technologies: Machine Learning, Image Processing, Convolutional Neural Networks (CNNs), TensorFlow, Image Analysis, Deep Learning
Project History
Vision-based Self-navigation System for Autonomous Vehicles
A simulation-oriented vision-based solution that I developed. It can perceive the surrounding environment, fuse multiple cameras, construct a 3D vector map of the environment, and do path planning and routing.
Vision-based In-cabin Monitoring System
An in-cabin monitoring system that I developed that only uses a smartphone's camera. The system includes:
• Gaze tracking and distraction detection.
• Facial expressions and mood classification for model selection and switching between manual and autonomous driving modes.
• Facial driving, including steering the car using head movements.
• Abnormal action detection.
• Lip reading to help command in noisy environments.
• Gaze tracking and distraction detection.
• Facial expressions and mood classification for model selection and switching between manual and autonomous driving modes.
• Facial driving, including steering the car using head movements.
• Abnormal action detection.
• Lip reading to help command in noisy environments.
Phoenix: The Smart Vehicle
This project involved working with a team to make a level-three self-driving car for Ain Shams University. The system was created for the vehicle to navigate safely on campus to help people with special needs.
I developed a deep reinforcement learning model from the PPO2 algorithm to control the vehicle, which was trained for weeks using multiple agents on the cloud. A single front-facing RGB camera was the only source feeding this model with additional segmentation and feature extraction models to help with scene understanding.
I developed a deep reinforcement learning model from the PPO2 algorithm to control the vehicle, which was trained for weeks using multiple agents on the cloud. A single front-facing RGB camera was the only source feeding this model with additional segmentation and feature extraction models to help with scene understanding.
CheckMate
A skilled AI player that I made that can search for millions of moves in seconds with a high probability of winning. I used alpha-beta pruning for tree search, quiescence searches to tackle the horizon effect problem, and the post-thinking algorithm to enhance the search accuracy.
Education
2015 - 2019
Bachelor's Degree in Computer Science
Ain Shams University - Cairo, Egypt
Certifications
JUNE 2023 - PRESENT
Microsoft Certified: Azure AI Engineer Associate
Microsoft
JULY 2018 - PRESENT
Graph Analytics for Big Data
University of California, San Diego | via Coursera
JUNE 2018 - PRESENT
Machine Learning With Big Data
University of California, San Diego | via Coursera
Skills
Libraries/APIs
PyTorch, OpenCV, TensorFlow, Pandas, NumPy, Azure Cognitive Services, Keras, TensorFlow Deep Learning Library (TFLearn), Node.js
Tools
Azure Machine Learning
Languages
Python, Python 3, C++, C
Platforms
Linux, Docker, Azure, Kubernetes
Storage
Azure Cloud Services, Neo4j, Graph Databases
Other
AI Programming, Artificial Intelligence (AI), Convolutional Neural Networks (CNNs), Image Processing, Image Analysis, Image Analytics, Object Detection, Computer Vision, PX4 Autopilot, Research, Machine Learning Operations (MLOps), Team Management, Tesseract, EasyOCR, Robotics, Digital Imaging, Simulations, Deep Learning, Deep Reinforcement Learning, Cloud, Machine Learning, Azure Cognitive Search, Game Theory, Graph Theory, Computer Science, Big Data
Collaboration That Works
How to Work with Toptal
Toptal matches you directly with global industry experts from our network in hours—not weeks or months.
1
Share your needs
Discuss your requirements and refine your scope in a call with a Toptal domain expert.
2
Choose your talent
Get a short list of expertly matched talent within 24 hours to review, interview, and choose from.
3
Start your risk-free talent trial
Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.
Top talent is in high demand.
Start hiring