Description
As a Staff Data Scientist at Zendesk, you will join the AI Security team and be responsible for designing and developing machine learning and AI approaches that help understand and identify anomalous activity and AI Security risks.
The role involves collaboration with Security Engineers, Software Engineers, ML researchers, and product teams to share actionable insights and models that can be used to keep Zendesk's customers safe and prevent product abuse.
Key Responsibilities
- Run and develop our AI Security evaluation platform to test Zendesk AI features.
- Analyze large volumes of behavioral and user interaction data to identify patterns of abuse, and automate methodology.
- Develop viable detection models and techniques using offline data that can inform and guide engineering implementation in production.
- Improve detection accuracy for existing spam detection projects while minimizing false positives.
- Collaborate with cross-functional teams to implement prevention strategies based on data insights.
- Stay up-to-date with the latest trends in AI Security.
- Mentor and provide technical leadership on projects.
- Collaborate with our Security and Product teams on emerging data challenges and provide data science expertise.
Required Qualifications
- Advanced degree in Computer Science, Statistics, Applied Mathematics, or related quantitative field, or equivalent practical experience.
- 5+ years of experience applying Machine Learning/Artificial Intelligence in areas such as fraud detection, anomaly detection, or security.
- Strong programming skills in SQL and Python, with proficiency in data processing frameworks.
- Fluency in AI-assisted programming (e.g., Claude Code, Cursor AI) and other AI tools to accelerate workflows.
- Experience with a variety of Statistical, Machine Learning, data mining, and time series techniques, including strong experience with the specifics of anomaly detection techniques and their statistical properties.
- Experience working with large datasets and distributed computing environments (e.g., Spark, Snowflake).
- Strong communication skills with the ability to translate complex technical concepts to non-technical collaborators.
Preferred Qualifications
- Proven track record implementing anomaly detection or AI Security evaluation systems at scale.
- Experience with AI Red Teaming tools.
- Knowledge of cybersecurity concepts and common attack vectors.
- Experience with Machine Learning model monitoring, maintenance in production, and customer impact of guardrails and firewall models.