Senior Data Scientist at Kard
About the Role
As a Senior Data Scientist at Kard, you will build and deploy machine learning and experimentation systems that power our card-linked offers platform. Your work will directly improve how users discover and engage with offers, and how partners measure ROI. You’ll operate across personalization, ranking, and causal measurement - partnering closely with Product, Engineering, and Sales to turn behavioral transaction data into production-grade models and insights.
Responsibilities
Build and ship ML models that drive offer personalization, ranking, and targeting using transaction, merchant, and user behavioral data.
Develop features and training pipelines on top of large-scale event and transaction datasets (e.g., spend patterns, visit frequency, merchant affinity).
Design and analyze A/B tests and incrementality experiments to measure campaign and model impact.
Apply causal inference methods (e.g., matching, uplift modeling, diff-in-diff) to quantify partner ROI and user behavior changes.
Partner with ML and Data Engineers to productionize models, including feature stores, batch/real-time scoring, and monitoring.
Improve and iterate on ranking/recommendation systems to optimize engagement, conversion, and retention.
Contribute to attribution and measurement systems that help brands understand incremental value from Kard campaigns.
Translate complex modeling outputs into clear, actionable insights for internal teams and external partners.
Own projects end-to-end: problem framing, data exploration, modeling, deployment, and post-launch evaluation.
Help define best practices for experimentation, model evaluation, and data quality across the team.
Desired Skills
6+ years of experience in data science, with meaningful experience in applied machine learning in production.
Strong experience with recommendation systems, ranking models, or personalization (e.g., propensity models, collaborative filtering, embeddings).
Solid grounding in statistics and experimentation, including A/B testing and incrementality measurement.
Experience with causal inference approaches for real-world observational data.
Proficiency in Python (pandas, scikit-learn, PyTorch/XGBoost) and SQL; experience working with large-scale datasets.
Experience working with event-driven or transaction-level data (fintech, ads, marketplaces, or similar domains preferred).
Familiarity with modern data/ML stacks (e.g., Spark, Airflow, dbt, feature stores, cloud platforms like AWS/GCP).
Experience collaborating with engineers to deploy models into production systems (APIs, batch jobs, real-time scoring).
Ability to connect modeling work to business outcomes like conversion, lift, retention, and ROI.
Strong communication skills; able to explain tradeoffs and results to both technical and non-technical audiences.
Pragmatic, product-minded, and impact-driven.
U.S. core business hours availability and willingness to travel for company meetings.