Data Scientist, Automation

Key Skills

Apache Hadoop, C++, Data science techniques, Java Programming, Machine learning techniques, MapReduce, Python Programming, PyTorch, Scala Programming, SQL, TensorFlow

Job Description

One of BlaBlaCar’s key strategic goals is to leverage data through Machine Learning in order to trigger growth opportunities. Data Science has been instrumental to successfully launching new services for the past two years, yet the potential for improvements is still massive. If you are looking for exciting challenges, impacting millions of users and working on a state-of-the-art cloud platform, come and join us!

You’ll join the growing data science automation team, whose mission is to create value within BlaBlaCar Operations using machine learning and algorithms.

Among many projects, the team delivers Machine Learning driven tools to optimize and scale our Bus Network in western Europe.

BlaBlaCar data stack is composed of the Google Cloud Platform suite (BigQuery, Pub/Sub, GKE, Cloud Run, ...).

Data scientists collaborate closely with ML engineers and Data analysts to deliver end-to-end ML projects from data exploration to production.

What you will contribute to:

• Leveraging machine learning algorithms to deliver the most efficient bus network to our users

• Contributing to pioneering research on experimentation on data science driven mobility

• Recommending and work with software engineers to implement real-time solutions

• As an experienced member in a team of 6 Data Scientists:

  • Challenging our data scientist toolbox, and proposing solutions to improve our data science tooling

  • Leading large-scale projects

  • Mentoring other data scientists

Qualifications

What you will need to be successful

• Have a minimum 3+ years of professional experience in Data or software engineering, including 1+ year as a data scientist building predictive machine learning models in production

• Pushed to production several ML based solutions and are familiar with retraining strategies

• Strong knowledge of Machine Learning theory, statistics and probabilities.

• Fluent in SQL, Python, and good knowledge of main machine learning packages: scikit, xgboost, keras...

• Possess good communication skills: you are able to explain your models clearly to both analysts and decision makers. You are able to move beyond the status quo

• Be humble, structured, organized, motivated by innovation and a relentless doer

• Enjoy working as a team-player and are willing to train others, share and learn more everyday

• Be fluent in English