Julien Hurault, Developer in Geneva, Switzerland
Julien is available for hire
Hire Julien

Julien Hurault

Verified Expert  in Engineering

Data Scientist and Developer

Geneva, Switzerland

Toptal member since October 14, 2021

Bio

Julien is a data scientist with six years of experience. I have worked across different industries, including automotive, pharma, logistic, banking, and aviation, for prestigious companies such as BMW, Johnson&Johnson, or Novartis. He combines software engineering skills like data engineering, ML, and DevOps with high business acumen, which allows him to quickly understand his customers' needs and deliver scalable productive solutions.

Portfolio

Axom
PyTorch, Deep Learning, DevOps, Amazon Web Services (AWS), Python...
Swiss Post
Python, Big Data, Data Science, Amazon Web Services (AWS), Data Analysis...
BMW
SQL, Simulation Engines, Process Simulation, Agent-based Modeling...

Experience

  • Machine Learning - 6 years
  • Python - 6 years
  • Python 3 - 6 years
  • Amazon Web Services (AWS) - 5 years
  • Deep Learning - 4 years
  • Docker - 2 years
  • Computer Vision - 2 years
  • DevOps - 2 years

Availability

Part-time

Preferred Environment

Python 3, Deep Learning, Amazon Web Services (AWS), Docker, Natural Language Processing (NLP), Generative Pre-trained Transformers (GPT), Computer Vision, Analytics, Data Science, Machine Learning Operations (MLOps), DevOps

The most amazing...

...project I have developed is hardware and software for a real-time defect detection system deployed on an industrial production line.

Work Experience

Founder | CTO

2018 - 2021
Axom
  • Led a team of three engineers with a mix of skills in deep learning and computer vision, industrial programming, web application, and hardware.
  • Developed industrial visual inspection systems based on deep learning for industrial production lines with high-quality standards within pharma, medical device, and watch industries.
  • Defined the complete development workflow: CI/CD, MLOps, containerization, coding standard, and documentation. I provided technical guidance and coding support when needed in various areas such as PyTorch, web application, C++.
Technologies: PyTorch, Deep Learning, DevOps, Amazon Web Services (AWS), Python, Computer Vision, Analytics, Named-entity Recognition (NER), Machine Learning, Docker, System Architecture, Text Categorization, Artificial Intelligence (AI), Natural Language Processing (NLP), Generative Pre-trained Transformers (GPT), Amazon Athena, AWS Lambda, AWS Elastic Beanstalk, Docker Hub, Git, DevOps Engineer, Data Engineering, Amazon S3 (AWS S3), Amazon EC2, Docker Compose, Machine Vision, Algorithms, Neural Networks, Manufacturing, Control Systems

Data Scientist

2015 - 2019
Swiss Post
  • Did machine learning for customer scoring, for large customer datasets.
  • Worked on data mining and data visualization for process optimization for large parcel tracking event datasets.
  • Did machine learning for predictive maintenance, for large machine log datasets.
Technologies: Python, Big Data, Data Science, Amazon Web Services (AWS), Data Analysis, Plotly, Pandas, Databases, SciPy, Python 3, Scikit-learn, SpaCy, Machine Learning, Generative Pre-trained Transformers (GPT), Natural Language Processing (NLP), Artificial Intelligence (AI), DataViz, Data Visualization, D3.js, Spark, PySpark, Scala, Big Data Architecture, Data Engineering, Analytics, Engineering, Apache Hive, SQL

Data Analyst

2014 - 2015
BMW
  • Analyzed and optimized the production system such as lead time and inventory disposal reduction, thanks to production data visualization (SQL) and predictive simulation discrete event simulation (DES).
  • Developed and implemented a decision support tool to calculate and compare the production costs between several investment scenarios.
  • Interacted with various stakeholders in production, controlling, and strategy.
Technologies: SQL, Simulation Engines, Process Simulation, Agent-based Modeling, Data Visualization

Experience

Industrial Computer Vision System

Industrial computer vision system detecting scratches or impacts on drugs and vials. This system realized real-time inferences on a video stream sent by an industrial camera; It was a full-stack system: hardware (server + GPUs) deep learning software PyTorch and user interface.

Automatic Text Classification

Automatic classification of texts written by process quality experts for a drug manufacturing company. Trained an entity recognition algorithm to detect context-specific words such as drug names, process names, department names.

Education

2013 - 2015

Master's Degree in Engineering

TU Munich - Munich, Germany

2010 - 2015

Master's Degree in Engineering

Ecole Centrale Lyon - Lyon France

Skills

Libraries/APIs

Pandas, PyTorch, SciPy, Scikit-learn, SpaCy, D3.js, PySpark

Tools

Named-entity Recognition (NER), Plotly, DataViz, Amazon Athena, Docker Hub, Git, Docker Compose

Languages

Python 3, SQL, Python, Scala

Paradigms

DevOps, Agent-based Modeling

Platforms

Amazon Web Services (AWS), Docker, AWS Lambda, AWS Elastic Beanstalk, Amazon EC2

Frameworks

Spark

Storage

Databases, Apache Hive, Amazon S3 (AWS S3)

Other

Analytics, Data Science, Machine Learning Operations (MLOps), Engineering, Machine Learning, Convolutional Neural Networks (CNNs), Deep Learning, Natural Language Processing (NLP), Computer Vision, Generative Pre-trained Transformers (GPT), Simulation Engines, Process Simulation, Big Data, Data Engineering, System Architecture, Text Categorization, Artificial Intelligence (AI), Data Analysis, Data Visualization, Big Data Architecture, DevOps Engineer, Machine Vision, Algorithms, Neural Networks, Manufacturing, Control Systems

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