impact.com
Sr. Data Scientist, Programmatic Algorithms
$165K–$185K
Victoria, British Columbia, Canada +1 · Senior · Full-time · Posted Apr 27, 2026
- Location
- Victoria, British Columbia, Canada
Columbus, Ohio, United States - Experience
- 5+ years overall, with at least 2+ years building and deploying ML models in the specified domains.
- Education
- Bachelor's in a quantitative field (CS, Statistics, Math, Engineering, Economics, or similar); Master's/PhD preferred.
About the job
Owns the end-to-end development and production deployment of machine-learning systems that optimize programmatic auction pricing, inventory allocation, and marketplace performance.
What you'll do
- Build and operate pricing, yield, and inventory-allocation models, including real-time auction inference.
- Own model data pipelines, feature engineering, production monitoring, experimentation, and model lifecycle.
- Measure model impact through online experiments and collaborate with product and engineering teams on implementation.
What they ask for
- 5+ years in data science, ML engineering, or quantitative research, including at least 2+ years deploying ML models in programmatic advertising, ad tech, marketplace optimization, or a closely related domain.
- Demonstrated understanding of programmatic auction mechanics and production ML, including real-time inference, monitoring, retraining, and SLO ownership.
- Experience building data pipelines, feature stores, and training infrastructure for high-volume, low-latency ML systems; strong Python and SQL.
- Strong grasp of causal inference and online experiment design; bachelor's degree in a quantitative field.
Nice to have
- Master's/PhD; direct SSP, DSP, or exchange-side yield optimization experience.
- Experience with contextual bandits, reinforcement learning, online learning, or GCP/Databricks tools.
Pay
$165,000 - $185,000 USD per year base salary; additional 5% variable annual bonus (amount not specified); RSU grant (amount not specified)
Tools
Python, SQL, scikit-learn, XGBoost, LightGBM, PyTorch/TensorFlow, Spark, Kafka
AI focus
Develops and deploys ML for auction pricing, bid shading, yield and inventory optimization, forecasting, and real-time decisioning; may use contextual bandits, reinforcement learning signals, and online learning.
Model-written summary · the original posting is authoritative