Data Scientist

Job description

Are you interested in applying your top-level analytics skills to help thousands of kids to excel in their educational career? Do you want to push the boundaries of EdTech? Become part of the data science team at Squla!

Your role:

You will use your knowledge of and experience in machine learning and predictive analytics to help the organization apply useful interventions in order to stimulate engagement, learning and user retention. Cooperating closely with the development and product teams, you will build scalable machine learning pipelines, that can be deployed offline as well as online. You will be responsible for the project from start to finish, i.e. from ideation, data collection and feature engineering to deployment, monitoring and iteration.

You will work with data of hundreds of thousands of users, who together answer approximately 1.7 million questions per day on our platform. Specific projects that you will work on include predicting quiz interruption, customer churn, and product feature adoption. In the future, you might also work on recommender systems, contextual bandits, and automatic content generation.

You have a pragmatic way of working, striking the right balance between model simplicity, explainability, and performance. You also understand the value of feature construction and engineering, and you possess the proper data wrangling skills to do so in large datasets. Further, you are able to clearly explain your modeling strategy, choices, and outcomes to both a technical and non-technical audience. Finally, you are also able and willing to occasionally help out with ad-hoc data analysis and reporting.

Your tasks:

  • Feature construction and engineering;
  • Building highly performant predictive models;
  • Building, deploying and maintaining machine learning pipelines for both offline and online purposes;
  • Working together with the development team to ensure stable and scalable model implementations;
  • Working together with the product team to identify and validate modeling choices;
  • Communicating modeling strategy, choices, and outcomes to stakeholders in the business

You will execute these tasks as part of our Amsterdam based data science team, reporting to the head of data science.

Job requirements

Who are we looking for?

We are looking for an experienced and pragmatic data scientist with a passion for education and learning. Furthermore, you have:

  • A masters degree in a relevant field (e.g. data science, artificial intelligence, statistics, econometrics, math);
  • At least two years of experience in a similar role;
  • Experience working with both Python and R;
  • Knowledge of relational databases (e.g. MySQL);
  • Knowledge of version control systems, in particular git;
  • Experience building cloud-based machine learning pipelines (aws, gcp, azure); 
  • Experience training and running machine learning models at scale in cloud environments;
  • Excellent communication skills in English.

Apart from that, it would be nice if you have:

  • Experience with Amazon Sagemaker
  • Eperience with Apache Airflow;