Senior Machine Learning Engineer

Censys is on a mission to provide comprehensive Internet intelligence and actionable threat insights. They are seeking a Senior Machine Learning Engineer to build models and systems that classify and enrich vast amounts of Internet data, contributing to the transformation of raw telemetry into high-quality datasets and insights.

Responsibilities:

• Build and improve machine learning models and data-driven systems that classify, cluster, label, and enrich Internet-observed assets and services
• Own the design and development of applied ML workflows that turn raw Internet telemetry into usable context for internal systems and customer-facing products
• Partner with engineering, research, security, and product teams to ensure we’re building the right models, datasets, and feedback loops to improve coverage and quality
• Leverage your experience in machine learning, data science, and software engineering to build various parts of the system, including components like: feature pipelines, training datasets, model evaluation frameworks, confidence scoring systems, and services that run in the cloud or on-prem

Requirements:

• 5+ years of experience in data science, machine learning engineering, or software engineering with applied ML responsibilities
• Experience building and deploying machine learning or statistical models in production environments
• Experience programming in Go/Python, and familiarity with software engineering practices for building maintainable systems
• Experience working with large datasets and building data pipelines for feature generation, training, or inference
• Proficiency with supervised and unsupervised learning techniques, such as classification, clustering, similarity scoring, or anomaly detection
• Ability to evaluate models using sound statistics and understand tradeoffs related to precision, recall, accuracy, and confidence
• Ability to write understandable, testable code with an eye towards maintainability
• Possess strong communication skills and can explain technical concepts, model behavior, and tradeoffs to engineers, researchers, and product managers
• Experience building classification, enrichment, or labeling systems for messy or partially labeled data
• Experience deploying models in containerized environments, like Kubernetes
• Experience with at least one cloud provider, like: AWS, Azure, or GCP
• Familiarity with feature stores, model serving, MLOps workflows, or tools for experiment tracking
• Familiarity with security, Internet measurement, or network-derived datasets