R
Staff Data Scientist, Identity
HybridFull-timeData ScienceEnterprise SoftwareeCommerce
Drive the research and development of machine learning models for identity resolution and fraud prevention, from initial research through integration into high-throughput production systems.
Responsibilities
- Set the research roadmap and technical standards for identity resolution
- Architect and advance an identity graph engine using graph models, transformers, and other machine learning methods
- Build scalable predictive and representation-learning models for large tabular, sequence, and graph datasets
- Guide research projects from concept through production deployment
- Integrate machine learning pipelines into real-time production environments with data engineering, software, and product teams
- Evaluate current academic research and apply relevant methods to practical problems
- Mentor senior data scientists
Requirements
- MSc or PhD in computer science, statistics, mathematics, or a related quantitative field
- At least 6 years of experience designing, training, and deploying complex machine learning models in large-scale production environments
- Expertise in transformers, deep neural networks, graph neural networks, or advanced tabular learning
- Practical experience with distributed data processing systems such as Spark or Databricks, and with graph databases or frameworks
- Technical leadership experience, including setting architectural direction and translating business requirements into algorithmic solutions
Nice to have
- Experience in fraud detection, risk management, or fintech
- Experience in identity resolution, entity disambiguation, link analysis, or complex network modeling
Benefits
- Equity for all employees
- Pension and Keren Hishtalmut
- Private medical insurance
- Additional time off for parents and caregivers
- Commuter and parking benefits
- Team events, meals, and fitness activities
- Volunteer opportunities and professional development programs