Security Data Science Engineer

Role Overview

• Build and deploy intelligent, data-driven systems that utilize machine learning and AI agents to enable real-time attack pattern identification, risk assessment, and proactive defense across Salesforce products and global infrastructure.
• Lead the integration of Large Language Models (LLMs) and autonomous agents with security data pipelines.
• Oversee the end-to-end lifecycle—including development, release, monitoring, and operation—of ML models and AI agents to ensure they deliver high-impact protection at scale.
• Develop autonomous AI agents capable of executing complex security tasks, such as performing advanced data correlations, identifying specific attack patterns, conducting automated penetration testing, and analyzing security impacts.
• Engineer platforms that synthesize large-scale security telemetry into actionable risk intelligence and automated decisions.
• Partner closely with security engineers, infrastructure teams, and product stakeholders to deeply understand the threat landscape and design solutions that address high-priority security problems.
• Apply LLMs and prompt engineering to automate generation of security insights, explanations, and response workflows from detections and anomalies.
• Continuously improve algorithmic performance with a focus on detection, classification, and behavioral modeling in security and threat intelligence domains.
• Collaborate effectively with team members and suggest improvements to reduce time-to-detection and mature our security ML platform.

Requirements

• 6+ years of industry experience with a demonstrated passion for crafting, analyzing, and deploying scalable machine learning solutions.
• Proven track record in machine learning engineering focused on security use cases, such as anomaly detection, malware classification, or behavioral modeling.
• Experience deploying, monitoring, and maintaining ML systems in cloud environments (specifically AWS or GCP).
• Consistent record of building ML products using modern lifecycle methodologies, including CI/CD, QA, and Agile practices.
• Expert-level proficiency in writing high-quality, well-documented, and tested code, with a strong preference for Python.
• Solid understanding of data transformations and analytics using libraries and languages such as Pandas, Scikit-learn, SQL, and Spark.
• Hands-on experience with standard ML and orchestration tools like mlFlow, Airflow, and Docker.
• Strong understanding of Statistics and Machine Learning methods, including the challenges associated with the end-to-end ML project lifecycle.
• Familiarity with Large Language Model (LLM) applications in security, including prompt engineering and the orchestration of AI agent workflows.
• Excellent communication skills with the ability to translate complex technical concepts for internal stakeholders and product teams.

Tech Stack

• Airflow
• AWS
• Cloud
• Docker
• Google Cloud Platform
• Pandas
• Python
• Scikit-Learn
• Spark
• SQL

Benefits

• time off programs
• medical
• dental
• vision
• mental health support
• paid parental leave
• life and disability insurance
• 401(k)
• employee stock purchasing program