Domaine d'activité
Recherche & Développement
Custom drying food ingredients
Marcq-en-Barœul, France
Type de contrat
Permanent Contract
3 to 5 years

Description de l'offre

In the context of the launch of an ambitious program to foster the use and valorization of data across the company, Lesaffre International seeks to accelerate and structure its data delivery capabilities and competences.


Reporting to the Head of Data  Science, the Data Scientist will join a team with several outstanding profiles (data scientists, Data engineers). The data Scientisit is a scientific data expert playing a key role in the data use cases’ framing, the statistical & AI modeling, and the development of Lesaffre Group data use cases. The Data Scientist will be part of “features team” that deliver innovative data use cases with various business domains and geographies across the company, such as:

  • Factory 4.0 data projects to optimize the production processes in the factories of Lesaffre, and involving factory sensor data
  • Data projects linked to state-of-art R&D regarding the expertise domains of Lesaffre (e.g., complex yeast strain screening, AI for genomics engineering, fermentation modulization etc..)
  • All relevant other data projects to optimize the group operations (supply chain optimization, demand sensing, etc.)


Main responsibilities

●        The Data Scientist designs the scientific methodology to solve business problems

○        Translate business challenges into scientific problems

○        Build efficient statistical or AI models

○        Communicate in a pedagogical way to Lesaffre group stakeholders

●        The Data Scientist supports the data use case framing

○        Make preliminary analysis to assess the data quality

○        Estimate the feasibility and the performance of a data-driven approach

○        List the data prerequisites to start a data use case

●        The Data Scientist develops data use cases and supports on the monitoring in production

○        Implement and structure the end-to-end data treatments and pipeline

○        Package AI models training and predict components

○        Define specific metrics to monitor the model performance in production



●        Master’s degree or PhD in engineering, science, computer science, machine learning, applied statistics, biostatistics, physics or mathematics

●        At least 3 years of experience on relevant roles (data scientist, machine learning engineer, senior data analyst, R&D engineer, biostatistician).

●        Hands-on experience with implementing data and AI models

●        Previous experience with technical/research/industrial data would be ideal


Technical skills

●        Machine learning and scientific methodology:

○        Experience in finding data science solutions to business problems

○        Good knowledge of statistical and data science concepts (e.g, model evaluation, overfitting, parameter tuning, null imputation)

○        Experience in data & AI modelling including both classification, regression and clustering problems in python using scikit-learn (e.g, linear models, random forests, gradient boosting, svm, knn, etc.)

○        Ideally at least one strong scientific expertise (e.g, interpretability, time series forecasting, genomics, image recognition, etc.)

●        Data analytics, processing and visualization:

○        Strong programming experience with data-related packages in Python (e.g., numpy, scipy, pandas, scikit-learn)

○        Additional programming experience in R would be a plus

○        Experience in data treatment (e.g, filter, aggregate, merge, etc.)

○        Experience in data visualization (e.g., seaborn, matplotlib, plotly, dash, Streamlit, PowerBi, Tableau)

○        Experience with data quality analysis (e.g., null values and outlier’s detection)

●        Data use case development and monitoring:

○        Programming experience in Python using virtual environment, typing, debugging, logging and testing

○        Experience with collaborative tools (e.g., git)

○        Experience in data storage and data modeling

○        Experience with at least one SQL and one NoSQL database (e.g., MySQL, MongoDB, CassandraDB)

○        Ideally experience in deployment and monitoring of data use case and/or AI model in production on Cloud (e.g., AWS, Azure, OVH, GCP)


Other skills

●        Strong science skills

●        Business and innovation oriented

●        good communication skills

●        Demonstrated ability to deliver in autonomy scientific data and ML methodology that answer to business needs

●        Full English proficiency. French proficiency is a plus.

Description de l'entreprise

A key global player in fermentation for more than a century, Lesaffre, with a 2,2 billion euro turnover, and established on all continents, counts 10,700 employees and more than 85 nationalities. On the strength of this experience and diversity, we work with customers, partners and researchers to find ever more relevant answers to the needs of food, health, naturalness and respect for our environment. Thus, every day, we explore and reveal the infinite potential of microorganisms.

To nourish 10 billion people, in a healthy way, in 2050 by making the most of our planet’s resources is a major and unprecedented issue. We believe that fermentation is one of the most promising answers to this challenge.