Staff Security Detection Engineer, Machine Learning

What you'll do

• Design and maintain machine learning models for anomaly detection using techniques like clustering, time-series baselines, and autoencoders.
• Operationalize models from development to production using detection-as-code, CI/CD pipelines, and automated response hooks.
• Engineer and tune features from identity, endpoint, network, cloud, and application telemetry to improve model signal quality.
• Partner with the SOC to triage detections, create feedback loops, and use analyst data to retrain models.
• Translate threat intelligence and fraud scenarios into repeatable, model-backed analytics with measurable precision and recall targets.
• Establish model governance including drift monitoring, data quality checks, and explainability controls.
• Participate in post-incident reviews to identify new signals and address coverage gaps in the detection pipeline.
• Mentor engineers and analysts on applied machine learning, data quality, and detection tuning.

What we're looking for

• Bachelor’s degree in computer science, data science, statistics, or a related field.
• 7+ years of experience building and operating machine learning models for detection or anomaly detection in production.
• Proficiency in Python and SQL using ML and data stacks like pandas, scikit-learn, PyTorch, or TensorFlow.
• Experience with big-data technologies such as Snowflake, Databricks, Spark, Delta/Iceberg, S3, or GCS.
• Knowledge of anomaly detection techniques including statistical baselining, clustering, isolation forests, autoencoders, and time-series methods.
• Understanding of security telemetry sources across identity, endpoint, network, cloud, and SaaS platforms.
• Familiarity with security frameworks and adversary tradecraft such as MITRE ATT&CK or the kill chain.
• Ability to communicate complex models, detections, and runbooks effectively to technical and non-technical stakeholders.