Data Scientist - Internship

Paris, France

Applications have closed

Shippeo

Shippeo is a global leader in real-time multimodal transportation visibility, helping major shippers and logistics service providers deliver exceptional customer service and achieve operational excellence.

View company page

Company Description

Founded in 2014, Shippeo is a global leader in real-time multimodal transportation visibility, helping major shippers and logistics service providers operate more collaborative, automated, sustainable, profitable, and customer-centric supply chains.

Hundreds of customers, including global brands such as Coca-Cola HBC, Carrefour, Renault Group, Schneider Electric, Total, Faurecia, Saint-Gobain and Eckes Granini, trust Shippeo to track more than 28 million shipments per year across 92 countries.

Having already raised €110 million in funding, Shippeo grows on average by 80% year on year. Our team of Shippians comprises 28 different nationalities, speaking a total of 24 languages.

 

Job Description

We are looking for an Intern in Data Science to join our Data & AI/ML tribe.

The Data & AI/ML tribe is responsible for leveraging the large amount of data that Shippeo has been acquiring over the course of running the platform and rolling it out to multiple shippers and carriers, to get insights from it. 

One of the main features the team builds and improves is Shippeo’s proprietary Machine

Learning algorithm that predicts Estimated Times of Arrival (ETA) of trucks, which is an extremely difficult exercise due to all the uncertainties in road transportation (traffic, weather conditions, driving regulations, time spent on on loading or delivery site, milk-runs that contribute to error propagation, etc.).

We are constantly looking for new ways to make the ETA prediction as accurate and reliable as possible, to help our users anticipate delays.

 

In the Shippeo platform, ETA is mainly used to answer the following customer needs:

1. When exactly will my truck arrive at the loading/delivery site?

2. Is there a risk of delay?

 

Our Machine learning algorithms are implemented and trained in an MLOps platform  including all the data ingestion, cleaning and transformation, ML model design and training, and model lifecycle management. In this context, we would like to explore different strategies to train our models and improve our model lifecycle management.

Strategies that would be explored includes:

  • Different data set rebalancing techniques [1]

  • Retraining frequency and automation [2]

  • A/B testing techniques

 

This internship will consist in exploring and proposing different strategies in order to improve our ML models performance, then implement the best performing solution in our MLOps platform. This will involve:

  • Understanding the current data pipeline used by Shippeo to train/predict its models.
  • Explore and test different data set rebalancing techniques.
  • Explore and test different retraining frequency and automation strategies.
  • Explore and test different A/B testing techniques.
  • Implement the best performing solutions in our in-production MLOps platform.

[1] C. Tantithamthavorn, A. E. Hassan and K. Matsumoto, "The Impact of Class Rebalancing Techniques on the Performance and Interpretation of Defect Prediction Models," in IEEE Transactions on Software Engineering, vol. 46, no. 11, pp. 1200-1219, 1 Nov. 2020, doi: 10.1109/TSE.2018.2876537.

 

[2] Machine Learning: The High-Interest Credit Card of Technical Debt

Qualifications

Your profile

  • You are pursuing a MSc degree (or equivalent) with a major in Data Science, and are in your final year 
  • Knowledge and experience with relational databases (SQL, data modeling)
  • Strong analytical skills with the ability to collect, organize, analyze, and disseminate significant amounts of information with attention to detail and accuracy
  • Programming skills in Python and experience with scientific programming libraries (Pandas, Numpy, Scipy)

Additional Information

Recruitment Process

  1. Preliminary call

  2. Technical interview and final interview

Our values

We are looking for talents who share our values:

  • 🚀 Ambition: we don't give up any challenge for Shippeo to become a global leader
  • 👫Team-spirit: we foster teamwork with respect in a relaxed atmosphere
  • 🤝 Commitment: we are demanding in order to achieve exceptional customer satisfaction
  • 😌 Simplicity: we stay simple in our behavior and their product

If you identify with our values and enjoy working in a fast-paced and international environment, Shippeo is just the place for you!

Would you like to discover more? Find us here👇

* Salary range is an estimate based on our AI, ML, Data Science Salary Index 💰

Tags: A/B testing Engineering Machine Learning ML models MLOps Model design NumPy Pandas Python RDBMS SciPy SQL Testing

Region: Europe
Country: France
Job stats:  44  12  0
Category: Data Science Jobs

More jobs like this

Explore more AI, ML, Data Science career opportunities

Find even more open roles in Artificial Intelligence (AI), Machine Learning (ML), Natural Language Processing (NLP), Computer Vision (CV), Data Engineering, Data Analytics, Big Data, and Data Science in general - ordered by popularity of job title or skills, toolset and products used - below.