yoinka

Senior Data Science

Merck

Rahway, NJFull TimeSenior$129k – $203.1k/yr
Sign in to applyVerified
Location
Rahway, NJ
Employment
Full Time
Work model
On-Site
Level
Senior
Salary
$129k – $203.1k/yr
Posted

Skills

AWSAzureComputer VisionCybersecurityDeep LearningLLMMachine LearningPyTorchPythonSQLServerlessSpark

About this role

Job Description

Position Summary We aspire to be the premier research-intensive biopharmaceutical company. We're at the forefront of research to deliver innovative health solutions that advance the prevention and treatment of diseases in people and animals. The Cyber Applied AI team is looking for a Senior Data Scientist to build detection and investigation analytics over enterprise security data. The work is statistical: finding unusual behavior in very high-volume network and endpoint telemetry, measuring similarity between security events, correlating alerts from multiple sources into unified incidents mapped to MITRE ATT&CK, and turning threat intelligence into structured, usable data. The person in this role takes an analytical method from idea through validation and into production, and owns the data pipelines that feed it. This is a senior individual contributor role for a data scientist who also engineers. The person in it designs the method, builds the pipelines and services that run it, deploys it on Azure or AWS, and keeps it in production. That includes applied AI work: building AI-driven analysis systems that use Model Context Protocol (MCP) tools over security data stores to automate investigation and shorten triage, and exposing results through APIs and automated reporting.

Responsibilities

Build and maintain statistical anomaly detection over network telemetry at the scale of billions of records per day, using behavioral baselines, percentile thresholds (p95/p99), new and rare entity detection, and feature engineering. Design correlation frameworks that use IDF weighting, entity similarity metrics, and MITRE ATT&CK mappings to aggregate EDR and other security telemetry into unified security events. Implement these methods as production workflows in Azure Data Explorer using KQL functions and materialized views. Evaluate detection and correlation methods with defined metrics (precision, recall, false positive rate, time to triage), validate them against labeled incidents and analyst feedback, and monitor for drift once in production. Build pipelines that extract CVEs, indicators of compromise, and other structured intelligence from unstructured sources such as security news and vendor reporting. Design AI-driven security analysis systems that use MCP tools against Azure Data Explorer and threat intelligence services to automate investigations and reduce triage time. Turn analytical methods into repeatable detection and investigation workflows with automated reporting. Design and operate the data pipelines that feed the analytics, including batch and streaming ingestion on AWS (S3, Lambda, Glue, Step Functions, Kinesis) and Azure. Write ETL/ELT transformations in Spark and Python for large cybersecurity datasets. Identify where a purpose-built analytical system can replace a commercial product and build it when the economics justify it.

Qualifications

Required Bachelor's degree in data science, Statistics, Physics, Mathematics, or a related quantitative field. At least 5 years building statistical or machine learning methods and engineering them into production systems, including the data pipelines, cloud services, and APIs around them. Hands-on experience with statistical anomaly detection, behavioral baselining, or similarity-based correlation on datasets in the hundreds of millions of records or larger. Experience with security telemetry (network, endpoint/EDR, cloud, or identity) and familiarity with the MITRE ATT&CK framework. Strong Python and SQL. Working experience with an analytics query language such as KQL and with Spark or PySpark. At least 3 years building data pipelines on Azure or AWS, including both batch and streaming ingestion. Able to explain a method and its limits to engineers, analysts, and managers. Preferred Master's degree in data science, Statistics, Physics, Mathematics, or a related quantitative field and at least 5 years of experience Production experience with Azure Data Explorer,

Listing verified . Applications go through the company's official careers site.

← Back to Yoinka