Fortinet Machine Learning Engineer 

United States, California, Sunnyvale 

748296647

Key Responsibilities

• Risk Modeling and Explainability: Develop probabilistic models and statistical frameworks to assess security risk in cloud environments, integrating data from network logs, user behaviors, and threat intelligence to provide actionable risk assessments.
• Model Development: Design, train, and evaluate machine learning models for threat detection, anomaly detection, and other cybersecurity applications, particularly within cloud-based infrastructure.
• Data Pipeline Engineering: Collaborate with data engineers to develop and optimize data pipelines that process, clean, and transform raw cybersecurity data into formats suitable for machine learning.
• Deployment and Optimization: Implement machine learning models in production environments, focusing on model optimization for high performance and scalability, especially in cloud-based or hybrid environments.
• Research and Prototyping: Stay current on the latest ML techniques and tools; prototype and experiment with new algorithms to continuously enhance our capabilities.
• Threat Analysis Collaboration: Work alongside threat analysts to incorporate domain expertise into model features, ensuring model relevance to real-world cyber threat scenarios.
• Automation and Monitoring: Develop automated tools for model training, evaluation, and monitoring to streamline processes and maintain model performance over time.
• Code Review and Mentorship: Participate in code reviews, provide feedback, and mentor junior engineers to foster best practices in the team.

Required Skills and Qualifications

• Education: Bachelor's or Master's degree in Computer Science, Data Science, Machine Learning, or other quantitative fields. PhD is a plus.
• Experience: 4+ years of experience in machine learning, data science, or a related field, with at least 2 years in cybersecurity or cloud-based environments.
• Technical Skills:
  • Proficiency in Python, including common ML libraries such as PyTorch, TensorFlow, and Scikit-Learn.
  • Experience with probabilistic and statistical modeling for risk assessment, anomaly detection, and classification algorithms.
  • Strong understanding of data preprocessing, feature engineering, and data pipeline design.
  • Knowledge of cloud computing platforms (AWS, Azure, GCP) and familiarity with securing and monitoring cloud infrastructure.
  • Familiarity with containerization (Docker, Kubernetes) and deploying ML models in production.
  • Experience with big data processing platforms and frameworks (Snowflake, Spark) is a plus.
• Domain Knowledge: Solid understanding of cybersecurity principles, including network security, malware analysis, incident response, and risk assessment in cloud environments.
• Analytical Skills: Ability to analyze large, complex datasets and develop actionable insights and recommendations, particularly within a cloud context.
• Problem Solving: Strong problem-solving skills with the ability to handle ambiguity and propose innovative solutions to complex cybersecurity challenges.
• Communication: Excellent written and verbal communication skills; able to explain technical concepts to non-technical stakeholders.

Preferred Skills

• Experience with real-time data processing or streaming data.
• Familiarity with cybersecurity standards, protocols, and compliance requirements.
• Prior experience working in cross-functional teams within a fast-paced environment.
• Knowledge of adversarial machine learning and techniques to make models robust to adversarial attacks is a plus.