Staff Data Scientist

## Responsibilities - Lead technical strategy and end-to-end delivery of ML models across credit risk, fraud, and marketing — spanning both batch and real-time inference use cases - Develop and evaluate neural network architectures (e.g., embeddings, sequential models) as complements to tree-based models, improving prediction accuracy where tabular approaches have limits - Apply causal inference techniques to measure treatment effects, improve decision-making, and move beyond correlational models - Build models to enterprise-grade standards: modular, well-tested code; reproducible pipelines; thorough documentation; and governance artifacts (model cards, validation reports, audit trails) that meet the reliability and compliance requirements of a regulated financial services environment - Champion model explainability and business trust via SHAP insights and clear communication with senior stakeholders - Manage the technical development of data scientists — guide complex projects, lead code reviews, and drive knowledge sharing across the team - Collaborate with business and executive leaders to identify and prioritize high-value DS initiatives - Drive an AI-first way of working — leveraging AI coding tools (e.g. Cursor, Claude Code) heavily across the DS workflow, from exploration and feature engineering to code review and documentation, and driving adoption across the team ## Requirements - 10+ years deploying production ML, driving commercial outcomes, and leading technical teams - Background in credit risk, fraud detection, or marketing ML in financial services - Deep proficiency in Python (pandas, polars, scikit-learn) and SQL; hands-on experience with Snowflake and/or Databricks, and familiarity with dbt - Tree-based model expertise: XGBoost, LightGBM, CatBoost — hyperparameter tuning, custom objectives, and SHAP-based explainability - Hands-on neural network development (PyTorch or TensorFlow) — embedding models, sequential architectures, and hybrid approaches to extend tree-based model performance - Cloud experience (AWS, GCP, or Azure) - Familiarity with MLOps processes and tooling — CI/CD for ML, model versioning, experiment tracking, and deployment pipelines - Proven track record managing and mentoring DS teams of 5+ members - Strong communication and executive stakeholder management skills - Hands-on experience with AI-powered development tools (Cursor, Claude Code) and a demonstrated habit of integrating them deeply into day-to-day data science work - Familiarity with model governance, audit trails, and compliance requirements for regulated ML ## Nice to Have - Experience with causal inference frameworks (e.g., DoWhy, EconML) applied to business decision-making - AWS experience (e.g. ECS, SageMaker) ## Benefits - Salary: We provide a strong base salary aligned with market ranges, along with the flexibility to tailor your mix of cash and equity to match your longer term goals. Final compensation is based on your skills, experience, and scope. For exceptional talent, we’re prepared to go above and beyond. - Equity Ownership (Where Eligible): At Neo, you don’t just work here, you own a piece of what we’re building. As a full-time team member, you share directly in the upside of one of Canada’s fastest-growing companies. When we win, you win — with real ownership and meaningful value. On-site, Calgary, AB.