Cybersecurity Data Scientist

This is a fully remote position, open to applicants in United States.

📋 Description

• Analyze unfamiliar data to determine its functions and establish baselines for users, roles, devices, and systems.

• Create detection and scoring methods utilizing peer group comparison, clustering, classification, outlier detection, and time series analyses.

• Optimize models using production data to minimize false positives while maintaining comprehensive coverage and ensuring performance adapts to changes in underlying systems.

• Establish evaluation criteria, measurement techniques, and drift detection protocols.

• Construct the data pipeline that supports models, from data ingestion and normalization to the reliable computation of features.

• Take ownership of the deployment and continuous operation of models in a production environment.

• Design visual representations that enable customer security leads to understand and scrutinize model outputs.

• Choose suitable models from statistical, classical machine learning, and language model categories, providing justifications for the selections made.

• Implement small and localized models where deployment limitations necessitate their use.

• Integrate AI coding tools into standard development practices.

⛳️ Requirements

• A bachelor's degree or higher in engineering, mathematics, statistics, or computer science.

• Over 5 years of experience applying data science within security, fraud, abuse, or risk domains, including models that are actively deployed in production.

• Advanced expertise in Python and SQL, with experience managing data volumes where the choice of tools can significantly impact results.

• Proven experience in anomaly detection, including population baselining, peer group comparisons, and data-derived thresholds.

• Capability to analyze base rates and alert volumes, including deriving the necessary precision based on population size and alert capacity.

• Experience in developing data pipelines.

• Experience in the deployment and maintenance of models in production, including version control, monitoring, and retraining processes.

• Practical experience using language models in a production setting.

• Ability to communicate technical findings clearly, both in writing and verbally, to audiences who may not have technical expertise.

• Willingness to travel to client sites up to 25% of the time.

🏝️ Benefits

• An annual performance bonus may be available for salaried roles.

• Additional benefits and perks may vary based on the position and terms of employment.

• A caring, enjoyable, honest, and autonomous workplace culture.

• A diverse and inclusive environment where employees feel valued and empowered.