Skip to main content
Empirical Security

Senior Data Scientist

RemoteNot specified
Published
Role
Data Science
Employment
Full-time
Salary not disclosed
Check eligibility

The listing doesn't say where it hires from. Check the description or the employer's site before applying.

No BS summary

A senior-level data scientist role building security-focused machine learning models in production for vulnerability prediction, with required experience in applied ML/statistics and work on class-imbalanced classification. Must be fluent in Python and SQL, and able to handle calibration, uncertainty, drift monitoring, and production model risk. The role is remote.

Core skills

PythonSQLMachine Learning

What you'll do

  • Own models and data end to end: problem framing, features, training, evaluation, deployment, and communication of risk ranking outcomes.
  • Design, train, and ship exploit prediction models against exploitation telemetry across cloud, appsec, and traditional infrastructure.
  • Build evaluations that track precision, recall, coverage, efficiency, and calibration over time.
  • Address extreme class imbalance in vulnerability exploitation modeling.
  • Work dual-model architecture topics including partial pooling, hierarchical priors, and cold-start behavior.
  • Engineer features from scanner output, EDR, asset inventory, identity, cloud posture, and exploitation telemetry while assessing leakage.
  • Own model monitoring and drift detection.
  • Publish papers, methodology write-ups, open benchmarks, and conference talks.
  • Partner with engineering and forward deployed teams to move models into production systems customers use.

What they require

  • Several years of applied machine learning or statistics with models that ran in production.
  • Fluency in Python and SQL, along with version control, reproducible pipelines, and secure handling of customer data.
  • Real depth in classification under heavy imbalance.
  • At least one of the following: survival and time-to-event analysis, Bayesian hierarchical modeling, or causal inference.
  • Strong calibration instincts and ability to reason about probabilistic outputs versus observed outcomes.
  • Ability to explain a model to a security executive and quantify uncertainty clearly.
  • Curiosity about attacker behavior and why features work.

Empirical Security is a quantum leap forward in exposure management, building custom models at scale to help organizations predict and prioritize the threats most likely to endanger them. Enterprises can no longer keep up with the flood of potential exploits caused by the AI era; only Empirical gives resource-strapped security teams the predictive capabilities to punch way above their weight class.

CybersecurityStartup
Salary not disclosed