Data Scientist, Classification and Scoring

Description

Lokker is a privacy platform. We continuously analyze websites, applications, third-party technologies and data flows to identify privacy, security and consent risks in production. We have built a large proprietary dataset from years of observing real-world digital behavior, and we are hiring a data scientist to help us expand and improve the classification, scoring and risk intelligence built on it.

You will develop and improve models that classify digital activity, identify meaningful privacy and security behaviors, and assess the confidence and significance of findings.

Looking for 2 to 4 years of production experience in data science and machine learning. Strong Python and SQL, pandas or Polars, scikit-learn and modern classification techniques, familiarity with model evaluation and explainability. Practical experience in training and evaluating supervised classification models on real PRODUCTION data, practical LLM experience beyond simple demonstrations, and curiosity about how websites and internet technologies actually behave. You do not need a privacy or adtech background. We will teach the domain.

You will work closely with engineering, product and privacy experts, and what you build goes directly into the product.

IMPORTANT: the timezone range above is a hard requirement, not a preference. We cannot make an exception.

ON APPLICATIONS: we assume you used AI to help write it. So do we. What we cannot do is verify a claim that exists only in the document you sent us, so make sure the skills you claim are visible somewhere public: LinkedIn with real dates and role detail, GitHub, papers, Kaggle, a writeup, a talk. If your best work is under NDA, say so and describe it in your own words.

A human reads every application. No keyword filter, no automated rejection.