Data Scientist

Summary

Join Feedzai's Data Science Team within Customer Success and contribute to a leading risk management platform. You will work closely with clients, utilizing critical thinking and a customer-focused approach. Responsibilities include data understanding, cleaning, preprocessing, feature computation, model tuning, and communication of findings. Collaboration with internal teams and clients is essential. The role requires expertise in machine learning, big data technologies, and programming languages. Feedzai offers a dynamic and collaborative environment.

Requirements

• MSc or PhD in Computer Science, Electrical Engineering, Statistics, Applied Mathematics, Physics or related field
• Proficient in Machine Learning (training and testing, avoiding overfit, etc.)
• Knowledge of Big Data technologies such as Spark, Hadoop and related
• Proficiency in bash, Python and either Java or Scala
• Knowledge of resource monitoring and runtime optimization (both at JVM and OS level)
• Ability to communicate your findings in a clear way

Responsibilities

• Understand the data which our clients provide to us
• Clean that data and validate that it is correct
• Preprocess the data, usually by using a mixture of shell scripts and a programming language such as Python, Java, Scala, etc
• Iteratively compute features and tune parameters to improve the quality of the model
• Communicate your findings to the project manager and assist him/her in decision making on the Data Science part of the project
• Work together with key stakeholders (data scientists, engineers, risk managers) from our clients
• Work with other parts of the organization (Product, Research, etc.) to improve processes, best practices and tooling

Preferred Qualifications

• Knowledge of statistics or data visualization is a plus
• Knowledge of tree based algorithms (Random Forests, XGBoost, LGBM) is a plus
• Knowledge of Deep Learning algorithms is a plus