Senior AI Scientist

Location: San Diego, California, United States

Salary: $165,500–$223,500 per year, with potential bonus, equity rewards, and benefits.

Company

hirify.global is a global financial technology platform offering products including TurboTax, Credit Karma, QuickBooks, and Mailchimp.

What you will do

• Design, build, deploy, monitor, retrain, and improve machine learning models detecting fraud and abuse across the customer lifecycle.
• Develop real-time and batch detection systems using entity-level anomaly detection, graph and link analysis, clustering, and behavioral modeling.
• Build data pipelines, discover data sources, engineer features, and partner with AI Engineering on production deployment.
• Apply generative and agentic AI to classify unstructured signals, explain model decisions, and automate investigation workflows.
• Run experiments and champion/challenger tests to determine operating thresholds and downstream actions.
• Partner with Policy, Investigations, ML Engineering, and Analytics to convert detection signals into enforcement actions and improve models.

Requirements

• MS or PhD in Computer Science, Statistics, Applied Mathematics, Operations Research, Physics, or a related quantitative discipline.
• 4+ years of industry experience building and deploying machine learning models in production.
• Expert proficiency in Python and SQL, with experience in scikit-learn, gradient boosting, PyTorch or TensorFlow, pandas, and NumPy.
• Strong knowledge of classification, regression, clustering, anomaly detection, neural networks, tree ensembles, class imbalance, noisy labels, and cost-sensitive evaluation.
• Experience with large-scale data ecosystems such as Spark, Databricks, or Hive, and comfort working in Linux.
• Ability to explain technical trade-offs to technical and non-technical stakeholders and connect model performance to business outcomes.

Nice to have

• Experience in fraud, risk, abuse, security, anti-money laundering, or other adversarial modeling domains.
• Knowledge of graph-based entity resolution, ring detection, link analysis, belief propagation, graph neural networks, or community detection.
• Experience with real-time model serving, feature stores, model monitoring, MLOps, or frequently retrained models.
• Production experience with LLM classification, evaluation methods, tool calling, or multi-step reasoning.
• Experience collaborating with investigations, operations, or policy teams where model output drives human review and enforcement.

Culture & Benefits

• Work within a distributed AI Science team in the Trust & Safety organization.
• Collaborate across Policy, Investigations, ML Engineering, Analytics, Product, Engineering, and Compliance.
• Potential eligibility for cash bonus, equity rewards, and employee benefits.
• Compensation follows a pay-for-performance approach and considers job-related skills, experience, and work location.