CONTEXT

At Wiremind, the Data Science team is responsible for the development, monitoring and evolution of all ML-powered forecasting and optimization algorithms in use in our Revenue Management systems. Our algorithms are divided in 2 parts:

• A modelling of the unconstrained demand using ML models (e.g. deep learning, boosted trees) trained on historical data in the form of time-series
• Constrained optimizations problems solved using linear programming techniques

The team is now entering a scaling phase where we will face the challenge to stay agile in terms of innovation while supporting and closely monitoring deployed algorithms. To address this issue, we organize our work around KubeFlow (https://www.kubeflow.org/), a MLOps tool empowering data scientists to focus on high added value tasks by maintaining a common framework and re-usable, modular components for all team members.

This rapid growth comes with a multiplication of data sources and deployed predictive models. In order to maintain high prediction accuracies and ascertain data quality, we are looking for an analytically-minded Junior Data Scientist with a strong academic background in statistics.

WHAT YOU WILL DO

You will be joining a team shaped to have all profiles necessary to constitute an autonomous departement (devops, software and data engineering, data science, AIML, operational research).

There, you will leverage state-of-the-art AI/ML methods and ironclad validation processes to deliver robust, interpretable prediction systems.

As Junior Data Scientist, you will be responsible for :

• Designing and applying statistical frameworks to evaluate the performance of new and existing models and their impact on client revenue
• Performing in-depth model and data analysis to identify points of improvement in our data engineering and modeling pipelines
• Developing performance monitoring tools with support from experienced ML and data engineers
• Taking part in the maintenance, development and search for new ML models through reproducible, well-documented and versioned pipelines

TECHNICAL STACK

• Python 3.7+
• KubeFlow over an auto-scaled Kubernetes cluster for orchestration
• Druid as datastore
• Common ML libraries: TensorFlow, LightGBM, XGBooost, Pandas, Dask, Dash
• Gitlab for continuous delivery

WHAT MATTERS TO US

• Advanced statistical literacy: bayesian inference, hypothesis testing, experiment design and analysis
• Hands-on experience with standard Python data analysis tools and frameworks: Pandas, NumPy, SciPy, StatsModels, PyStan
• A pragmatic, prod-oriented approach to ML: frequent, incremental gains beat a grand quest for perfection

WHAT WOULD BE A PLUS

• Strong computer science background in Python, with a keen interest for code quality and best practices (unit testing, pep8, typing)
• A first experience in a pricing-related domain