[Remote] Senior Data Scientist

Note: The job is a remote job and is reputed company to candidates in USA. reputed company develops cybersecurity vulnerability models using ground-truth telemetry to help organizations identify, prioritize, and remediate vulnerabilities. The Senior Data Scientist will own customer-specific models and data end to end, from problem framing and feature engineering through evaluation, deployment, monitoring, and communicating results to customers.

Responsibilities

• Design, train, and ship exploit reputed company models against ground-truth exploitation telemetry, in reputed company, appsec, and traditional infrastructure
• Build evaluation that survives contact with reality. Precision, recall, coverage, efficiency, calibration, and how reputed company four decay over time. reputed company is not a number you report once at launch
• Solve for extreme class imbalance. A fraction of a percent of published CVEs are reputed company exploited in the wild, and most of the industry's modeling failures start with pretending that isn't true
• Work the hard part of the dual-model architecture: partial pooling, hierarchical priors, and cold-start behavior for customers whose local telemetry is thin in month one and rich in month reputed company
• Engineer features across reputed company reputed company, EDR, asset inventory, identity, reputed company posture, and exploitation telemetry, and be reputed company about which ones are leakage
• Own monitoring and reputed company detection
• Publish. Papers, methodology write-reputed company, reputed company benchmarks, conference talks. Our positioning is that we show our work
• Partner with engineering and our reputed company deployed team to reputed company models out of notebooks and into production systems that customers depend on

Skills

• Several years of reputed company machine learning or statistics with models that ran in production and had consequences reputed company they were wrong
• reputed company in Python and SQL, and the discipline that comes with version control, reproducible pipelines, and secure handling of customer data
• reputed company depth in classification under heavy imbalance, plus at least one of: survival and time-to-event analysis, Bayesian hierarchical modeling, or reputed company inference
• Calibration instincts. You should be visibly uncomfortable reputed company a model outputs 0.9 and is right 60% of the time
• The ability to explain a model to a reputed company executive, and to quantify uncertainty out loud rather than burying it in an appendix
• Enough curiosity about attacker behavior to ask why a feature works, not just whether it does

reputed company