Senior Data Scientist

Verkor is a French industrial company aiming to pioneer low-carbon battery manufacturing in France. With the backing of prominent industrial companies such as Renault Group, Plastic Omnium and Schneider Electric, Verkor intends to electrify the future of European mobility.
 
With over 1100 experts from 53 different countries, our endeavor is to unite exceptional global talent to bring this ambitious and innovative project to life. Our strong and agile international team continues to grow and adapt to new challenges. Based in Grenoble and Dunkirk (France), we have started operations our Verkor Innovation Centre (R&D centre and 4.0 pilot line) which is now fully running and operational.
 
We now focus on enabling  the successful start of production of our Gigafactory in Dunkirk (France). With this facility, our ambition is to ramp-up mass production of low carbon lithium ion batteries to facilitate the decarbonization of European mobility.  
 

Main Responsibilities :

• Turns business questions into analytical and data science problems


• Defines success metrics and evaluation criteria aligned with business outcomes


• Analyze and explore structures and unstructured data to identify patterns, trends and anomalies


• Build production grade automation workflows


• Assess data quality, completeness, bias and limitations


• Identify additional data sources needed to improve analysis or models


• Perform data transformation for modelling purposes


• Model development and validation


• Interpret model results and analytical findings in business terms


• Communicate findings clearly to non-technical stakeholders


• Document assumptions, limitations and risks of the model


• Works with operators and production/quality technicians to understand objectives, constraints and decision needs


• Work with data engineers /Digital team to operationalize data preparation when needed.


• Works with data scientists and CAE experts to understand the value of the project and how it links with the roadmap.

• 8 - 11 yrs of Experience


• Masters or PhD in Data science/ Applied mathematics/Statistics


• Experience working with large-scale data sets in an industrial environment


• Strong fundamentals of linear algebra, Calculus, probability and statistics.


• Solid understanding of distributed systems concepts, data partitioning and parallel processing


• Hand-on experience using databricks for data exploration, analysis, feature engineering and model training


• Strong proficiency in Apache spark (dataframes, SQL, ML lib concepts), for large scale data processing, with hands-on experience in distributed model training using Pytorch or tensor flow.


• Databricks notebooks (Python/SQL)


• Experience in Knowledge Graph a plus


• Strong proficiency in pandas and numpy for exploration, feature engineering and analytical workflows


• English & French are both mandatory

Cette annonce provient de Lever. Voir l'annonce originale ↗