SpyCloud-posted about 2 months ago
Full-time • Mid Level
Austin, TX
101-250 employees
Publishing Industries

We're looking for a Applied Machine Learning Engineer to design, build, and deploy ML-driven solutions for critical cybersecurity use cases like threat intelligence, incident detection, and risk scoring. You'll own the full machine learning lifecycle-from prototyping to deployment in production-and work closely with engineering, product, and research teams to turn complex problems into scalable and efficient ML systems. This role is ideal for someone who thrives in applied, hands-on environments where impact and collaboration matter. As an Applied Machine Learning Engineer, you will develop, train, and deploy machine learning models using real-world structured and unstructured data to power critical security features such as threat detection and alerting, entity resolution and risk scoring, and natural language-based tagging and classification. You'll be responsible for building scalable preprocessing and feature engineering pipelines to ensure robust model performance in production. Additionally, you will own model monitoring and evaluation, designing feedback loops to continuously improve accuracy and effectiveness. Working closely with software engineers, you'll help productionize these models in modern cloud-native environments like AWS. This role is highly collaborative. You'll partner with product managers and domain experts to define machine learning requirements and success criteria, rapidly prototype MVPs to test new features or signals, and work with data engineering teams to access, clean, and transform diverse data sources. Your input will also contribute to broader system design and architectural decisions involving machine learning components. Strong communication and documentation skills are essential. You will clearly articulate model design choices, tradeoffs, and outcomes to both technical and non-technical stakeholders. Maintaining thorough documentation for models, pipelines, and evaluation methodologies is part of your workflow, along with participating in model and compliance reviews and, when needed, engaging in customer-facing discussions.

  • Develop, train, and deploy machine learning models using real-world structured and unstructured data to power critical security features such as threat detection and alerting, entity resolution and risk scoring, and natural language-based tagging and classification.
  • Build scalable preprocessing and feature engineering pipelines to ensure robust model performance in production.
  • Own model monitoring and evaluation, designing feedback loops to continuously improve accuracy and effectiveness.
  • Help productionize these models in modern cloud-native environments like AWS.
  • Partner with product managers and domain experts to define machine learning requirements and success criteria, rapidly prototype MVPs to test new features or signals, and work with data engineering teams to access, clean, and transform diverse data sources.
  • Clearly articulate model design choices, tradeoffs, and outcomes to both technical and non-technical stakeholders.
  • Maintain thorough documentation for models, pipelines, and evaluation methodologies.
  • Participate in model and compliance reviews and, when needed, engaging in customer-facing discussions.
  • 5+ years of experience building and deploying machine learning systems in production
  • Strong background in applied math (linear algebra, optimization, statistics) and machine learning
  • Proficiency in Python and key ML libraries: PyTorch, TensorFlow, scikit-learn, XGBoost
  • Experience building scalable data and ML pipelines (e.g., with Airflow, Spark, Pandas)
  • Hands-on experience deploying ML models into cloud environments or containerized services
  • Strong communication skills and the ability to translate complex problems into actionable solutions
  • Experience with CI/CD, versioning (e.g., MLflow, DVC), and model monitoring in production environments
  • Experience with Natural Language Processing (NLP) for text classification, tagging, or entity extraction
  • Familiarity with cybersecurity datasets or domains: threat intelligence, account takeover, ransomware, etc.
  • Exposure to graph analytics, knowledge graphs, or cybersecurity frameworks like MITRE ATT&CK
  • Background working with unstructured data (e.g., log files, threat reports, breach datasets)
© 2024 Teal Labs, Inc
Privacy PolicyTerms of Service