Staff Data Scientist

Bitsight•Boston, MA

1d•$125,000 - $189,000

About The Position

Bitsight is a cyber risk management company that helps organizations manage exposure, performance, and risk. Methodology data scientists research, develop, and implement statistical and machine learning methodologies to assess cybersecurity risks. In this Staff Data Scientist role, you will develop predictive cyber risk models, maintain and enhance Bitsight’s Security Ratings and Risk Vector methodologies, and translate analytical solutions into scalable production systems. You will collaborate with Engineering, Product Management, Marketing, Customer Success, and other teams to build robust, explainable, data-driven solutions to cybersecurity problems.

Requirements

Master’s degree required in Statistics, Applied Mathematics, Computer Science, Physics, Engineering, or another quantitative science; a Ph.D. is preferred.
At least 1 year of equivalent industry experience at the staff level.
Experience with Git, Python or R, SQL, software SDLC and package/library development, shell or bash command-line scripting, big data technologies such as Spark or Hadoop, applied machine learning, predictive modeling, statistical analysis, model validation, data visualization and reporting tools, and AWS.
Ability to manipulate, clean, and combine large, complex, disparate data sources.
Ability to read, learn, and communicate algorithms and statistical methodologies from peer-reviewed literature.
Hands-on experience using AI-assisted development tools such as Claude Code, Cursor, or GitHub Copilot to improve coding, analysis, testing, and development productivity.

Nice To Haves

Ph.D. in Statistics, Applied Mathematics, Computer Science, Physics, Engineering, or another quantitative science.
Prior experience modeling risk for rare events.

Responsibilities

Research, develop, validate, and implement statistical and machine learning methodologies for cybersecurity risk assessment and prediction.
Maintain and enhance Bitsight’s Security Ratings and Risk Vector scoring methodologies, ensuring accuracy, robustness, and explainability.
Explore cybersecurity, threat intelligence, and firmographic data sources to improve existing models and develop new capabilities.
Explore and apply emerging AI and machine learning techniques and tools to solve complex cybersecurity problems.
Develop and maintain scalable, reliable, well-documented, and tested code for data science models, scoring algorithms, and data processing pipelines.
Monitor model performance, investigate anomalies, and identify opportunities for improvement.
Communicate complex technical concepts and contribute to internal and customer-facing documentation.
Anticipate technical issues at the product level and make design decisions to avoid them.