Data Scientist

Responsibilities

  • Designing, implementing, evaluating, and improving statistical models and machine learning algorithms (classic and deep neural networks)
  • Evaluating promising technologies (e.g. frameworks, libraries, third-party integrations)
  • Staying up to date with the state of ML applications in education (esp. adaptive learning and predictive learning analytics)
  • Creating technical documentation, incl. patent applications
  • Sharing work results internally and externally (e.g. talks and workshops at conferences and meetups, journal publications)
We work in agile teams in which members can wear many hats, so besides building models, or data scientists also have the opportunity to work on other project aspects, e.g. designing efficient solutions for large-scale data processing, operationalizing and optimising models, etc.

Skills

  • Theory and practice of machine learning: gradient boosting, e.g. XGBoost,  Deep Learning models

  • Descriptive and mathematical statistics

  • Psychometric models, e.g. Item Response Theory, Bayesian 

  • Programming skills, especially Python, awareness of best programming practices

  • Hunger for knowledge

Tools

  • Python libraries:  TensorFlow, Keras,  XGBoost, scikit-learn

  • Stan, greta

  • SQL, Snowflake
  • Spark, Databricks

  • Amazon Web Services (Redshift, Athena, EMR); Google Cloud equivalents

Example projects

  • Finding the worst performing content in an e-learning product

  • Estimating text difficulty

  • Student skill profiling

  • Creating adaptive assessment systems that

    • learn new skills quickly

    • fill the gaps in the knowledge

  • Identification of students at-risk of failing a course

  • Scoring of speech fluency

  • Automated generation of activities