Data Scientist, Classification and Scoring
Help build the models that turn complex web and application activity into accurate, explainable privacy and security intelligence.
About Lokker
Lokker helps organizations understand and control how data is collected and shared across their digital properties. Our platform continuously analyzes 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. We are hiring a data scientist to help turn that data into increasingly accurate classification, scoring, and risk intelligence.
The Role
You will develop and improve models that classify digital activity, identify meaningful privacy and security behaviors, and assess the confidence and significance of findings.
Explainability matters. Our findings are used by privacy teams, engineers, lawyers, and insurers, so models need to produce outputs that are both accurate and understandable.
This is primarily a structured-data machine learning problem, with opportunities to use LLMs and other techniques where they add meaningful value.
What You'll Work On
- Develop and improve production classification models
- Build features and signals from large-scale behavioral and network data
- Improve training data, labeling, evaluation, and model quality
- Develop confidence and risk-scoring approaches that support product decisions
- Produce explainable outputs that help users understand why a finding matters
- Build evaluation, regression, and monitoring systems to maintain model quality over time
- Explore new approaches for identifying emerging privacy and security risks
What We're Looking For
- 2–4 years of production experience in data science, machine learning, or data engineering
- Strong Python and SQL
- Experience with pandas or Polars, scikit-learn, and modern classification techniques
- Experience working with messy, imperfect, or imbalanced real-world datasets
- Solid grounding in supervised learning — you can frame a classification problem, choose the right metrics, and design validation that holds up in production
- Rigorous evaluation of model output — you can tell when strong metrics mask overfitting or slice-level failure, not just when a number looks good
- Practical experience using LLMs beyond simple demonstrations
- Familiarity with containerization and cloud services
- Curiosity about how websites, applications, and internet technologies actually behave
You do not need a privacy or adtech background. We will teach the domain.
Bonus Experience
Experience with privacy, advertising technology, web analytics, entity resolution, anomaly detection, cloud data platforms, browser automation, or large-scale web data is helpful but not required.
Why This Role Matters
Lokker already captures a unique view of how digital systems behave in the real world. This role helps turn that data into intelligence customers can act on.
You will work closely with engineering, product, and privacy experts, and what you build will go directly into the product. It is an opportunity to work on difficult applied machine-learning problems with proprietary data and immediate real-world impact.