Senior Data Scientist

Who We Are

• Sonatype is the software supply chain security company. We deliver the industry’s most complete solution for securing the modern software development lifecycle—from open source intake to production deployment. With tools that proactively detect malicious packages, manage SBOMs at scale, and optimize open source usage, we empower developers to build faster and safer software
• As the creators of Nexus Repository and stewards of Maven Central, we’ve shaped how developers consume open source for over a decade. Today, more than 15 million developers and 2,000 organizations—including 70% of the Fortune 100—rely on Sonatype to secure and scale their software supply chains.

The Opportunity

• We’re looking for a Senior Data Scientist to join our growing AI & Data Science team. You’ll lead the development of cutting-edge machine learning models to detect malicious behavior, surface anomalies, and enhance security posture across our platform.
• You’ll work with massive, complex datasets collected from millions of software components and behavioral signals. In this role, you’ll have significant autonomy to explore novel ML and generative AI approaches—and be part of a deeply collaborative cross-functional team alongside data engineers, product managers, and security experts.

What You’ll Do

• Own the end-to-end development of machine learning models, from research and prototyping through deployment and monitoring
• Explore and apply generative techniques (e.g., GANs, VAEs, LLMs) for fraud detection, anomaly detection, and behavioral analysis
• Design and implement experiments to evaluate model performance, reliability, and generalization
• Partner with data engineers to build scalable pipelines for data collection, preprocessing, and feature engineering
• Conduct exploratory data analysis and statistical modeling to extract insights from structured and unstructured data
• Work closely with product and domain experts to frame problems, translate requirements, and identify impactful opportunities
• Stay current on research advancements and assess how emerging methods (e.g., LangChain, HuggingFace models) can improve our platform
• Present findings clearly to stakeholders—both technical and non-technical—and drive data-driven decision making
• Mentor junior team members and contribute to the technical growth of the data science function

What We’re Looking For

• Minimum Qualifications
• 8+ years of experience in applied data science, machine learning, or AI research
• Strong foundation in computer science, mathematics, or a quantitative discipline
• Deep experience in generative modeling, deep learning architectures, and anomaly detection
• Strong Python skills and proficiency with ML libraries (e.g., TensorFlow, PyTorch, Scikit-learn)Proven success developing models in production settings with large-scale or noisy data
• Strong grasp of evaluation metrics, cross-validation, and best practices for building trustworthy models
• Hands-on experience with Jupyter or Databricks notebooks
• Excellent problem-solving and communication skills, with the ability to simplify complexity
 
• Bonus Points
• Familiarity with fraud detection systems or behavioral analytics in a cybersecurity context
• Experience with Databricks, AWS (e.g., S3, EMR, SageMaker), and cloud-native data environments
• Exposure to tools like MLflow, HuggingFace Transformers, LangChain, and PySpark
• Experience collaborating with data engineering teams working in Java/Scala
• Git proficiency and comfort with collaborative workflows (GitHub preferred)

Why You’ll Love Working Here

• Autonomy + Impact: Lead innovative AI work that directly secures millions of developers
• Modern Stack: Work with top-tier tools like Databricks, HuggingFace, and AWS SageMaker
• Collaborative Culture: Join a team that values trust, ownership, and continuous learning