Mohammed Benslimane
Verified Expert in Engineering
Machine Learning Developer
Mohammed is an artificial intelligence (AI) expert. He previously oversaw AI at one of the cutting-edge startups in deep learning in Europe. After graduating from top institutions, he worked for more than seven years in the conception of machine learning (ML) models, from proof of concept to industrialization in the Cloud or embedded devices. Mohammed's work with ML is very expansive and covers real-time recognition of groups of people, satellite imagery, and various systems.
Portfolio
Experience
Availability
Preferred Environment
Ubuntu Linux, GitHub, Docker, Kubernetes, Visual Studio Code (VS Code), Amazon Web Services (AWS), TensorFlow, PyTorch, Slack
The most amazing...
...project I've worked on is a recognition system engine in crowded areas deployed on 1,000 cameras by being RGPD compliant and attested as a leading solution.
Work Experience
Computer Vision Expert for Fishing Optimization Tool
BioSort AS
- Designed and implemented the computer vision stack from R&D to an ML production pipeline. Contributed to the roadmap and strategy design and planning.
- Developed an advanced (2D and 3D) and accurate camera calibration tool (< 1-pixel error). Features include intrinsic and extrinsic camera calibration, pose estimation, and depth estimation, among others.
- Developed the fish ID (identification of each individual fish) based on ad hoc deep learning landmarks through various stereo sensors (3D object detection, tracking, and reidentification on highly occluded and crowded fish scenes) in real time.
Machine Learning Engineer
PTSDx LLC
- Performed medium-level resolution pupillometry research for pupil segmentation. Developed an algorithm capable of segmenting pupils (<0.1 mm accuracy) in real time for PTSD detection based on Smartphone sensors.
- Contributed to API deployment, design, and integration. Everything was delivered within budget and according to the deadline.
- Participated in the design of the clinical trial for PTSD detection with psychiatrists to be FDA approved, which involved statistical analysis, hypothesis testing, and protocol definition.
Lead Machine Learning Engineer
Norbert Health
- Led the Norberth Health engineering machine learning team in the design, implementation, deployment, monitoring, and testing of several core features in their embedded device product, a Jetson Nano processor.
- Developed a remote photoplethysmography (rPPG) algorithm for accurate heart rate and heart rate variability (HR and HRV) with 95% accuracy completed compared to oximeter values.
- Developed a recommendation system based on vital signs and patient metadata for optimal health monitoring. Monitored areas included diet, sleeping hours, doctor appointments, and health insurance.
- Developed and led the shipping of a proprietary neural network architecture convenient for thermal (IR) and RGB sensors for patient recognition. Increased accuracy by 20% and ten times more FPS than the old algorithm (FaceNet and Chinese whispers.).
- Designed and implemented large-scale pub/sub message queues using Apache Kafka streams to process the IoT metadata and create Kafka topics for application and system logs.
Head of Artificial Intelligence
Digeiz
- Outperformed competition with a real-time multi-camera (3D or 2D) recognition engine for crowded locations by being GDPR compliant, verified by Bureau Veritas in Paris (98% mean average precision.) Deployed an average of 1,000 cameras per client.
- Tripled the inference time by maintaining the same infrastructure and accuracy of a popular object detection model on TensorRT. Compared to the existing state-of-the-art implementation, it created a cost-competitive advantage.
- Led expertise in real-time multi-object tracking in highly crowded areas. Patented a multi hypothesis tracking approach based on an efficient architecture of graph modeling with CUDA to solve the maximum weighted independent set problem.
- Monitored the technical deployment of our product at ten commercial malls, with 1,000 cameras per mall on average. Checked bug fixing and hardware limitations.
- Helped the commercial team to bring value from data to quantitatively assess the potential of accurate footfall transcripts in supporting retail innovation in the shopping center industry.
- Hired and managed a team of four talented R&D engineers.
- Created scientific road-maps on Jira while accompanying the embedded team to make C++ architecture for code production.
- Orchestrated the AI stack for optimal research collaboration, including infrastructure and an R&D coding and testing environment.
Data Scientist
Kayrros
- Developed the Kayrros Oil index for weekly oil volume production and storage prediction. Ensured 99.5% accuracy compared with quarterly public available volume data.
- Processed satellite images (Sentinel 1 and Sentinel 2) to detect drilling activity based on oil basin texture spatial variance. Developed a critical feature for volume prediction using a CNN-LSTM based model.
- Developed a text recognition (OCR) and topic detection on commodity reports scrapped weekly, with low and very dense reports.
- Developed real-time streaming applications integrated, using Kafka and PySpark. Handled large volume and velocity streams of structured and unstructured data in a scalable, reliable, and fault-tolerant manner to deliver real-time metrics for clients.
- Processed satellite images (Sentinel 1 and Sentinel 2) to predict the demand volume of oil using road segmentation with 95% accuracy.
Data Scientist
Adot
- Built real-time bidding algorithms based on contextual reinforcement learning, including a 30% cost optimization for the same CTR.
- Reduced the training time of a model used as a prior on ad space value segmentation by 90% while integrating it with Hyperopt and MLflow, which enabled us to perform hyperparameter tuning at scale and deliver value faster.
- Created and produced a machine learning model from scratch capable of detecting users on different devices (smartphones, laptops, desktops, and tablets), which led the company to change its marketing positioning.
Experience
Robust Tracking Using a Collaborative Model
I developed a sparsity-based discriminative classifier (SDC) and a sparsity-based generative model (SGM). Results outperformed state-of-the-art technology (MOT challenge) in complex scenes.
Reinforcement Learning in Algorithmic Trading
Skills
Languages
Python, SQL, C++, Scala
Libraries/APIs
TensorFlow, PyTorch, TensorFlow Deep Learning Library (TFLearn), NumPy, Pandas, Scikit-learn, Keras, PySpark, Camera API, OpenCV, Node.js
Tools
GitHub, MATLAB, GIS, Git, Slack
Paradigms
Anomaly Detection, Siamese Neural Networks, Data Science, Management, ETL
Platforms
NVIDIA CUDA, Ubuntu Linux, Docker, Apache Kafka, Amazon Web Services (AWS), Kubernetes, Visual Studio Code (VS Code)
Storage
MySQL, Amazon S3 (AWS S3), Elasticsearch
Other
Data Mining, Machine Learning, Deep Learning, Artificial Intelligence (AI), Computer Vision, Recommendation Systems, Predictive Modeling, Real-time Bidding (RTB), NVIDIA TensorRT, Convolutional Neural Networks (CNN), Directed Acrylic Graphs (DAG), Image Recognition, Classification, Neural Networks, Time Series Analysis, Algorithms, Mathematics, Statistics, Data Analysis, Statistical Analysis, Object Detection, Applied Mathematics, Natural Language Processing (NLP), Finance, Pricing, Data Visualization, Satellite Images, Long Short-term Memory (LSTM), Time Series, Healthcare Services, Autonomous Navigation, Point Clouds, GPT, Generative Pre-trained Transformers (GPT), Global Project Management, Reinforcement Learning, Econometrics, Behavioral Economics, Remote Photoplethysmography (rPPG), Clustering, OCR, Deep Reinforcement Learning, Trading, Bayesian Inference & Modeling, Probabilistic Graphical Models, Depth Estimation, Health, Biometrics, ML Pipelines, Object Tracking, Geometry
Frameworks
Spark, Apache Spark
Education
Master's Degree in Mathematics, Vision, and Machine Learning
Ecole Normale Supérieure - Paris, France
Engineer's Degree in Informatics and Applied Mathematics
Ecole Centrale Paris - Paris, France
Master's Degree in Economics
ETH Zurich - Zurich, Switzerland
How to Work with Toptal
Toptal matches you directly with global industry experts from our network in hours—not weeks or months.
Share your needs
Choose your talent
Start your risk-free talent trial
Top talent is in high demand.
Start hiring