Keystone.AI is seeking a Staff Applied Scientist specializing in Causal Inference to help advance our next-generation measurement capabilities. Our team builds scientific systems that power decision-making across industries, enabling clients to evaluate and optimize their most critical initiatives through rigorous causal analysis. This role will focus on applying and developing scalable causal inference methodologies on large-scale datasets to quantify the impact of interventions and improve strategic planning.
Requirements
- Experience with causal machine learning frameworks and structural causal models.
- Experience with time series methods for causal analysis.
- Proficiency with statistical programming languages such as Python, and experience deploying causal inference algorithms in production settings.
- Experience applying causal inference methods in large-scale, real-world settings (e.g., experimentation in digital platforms, pricing interventions, operational policy changes).
- Familiarity with advanced causal inference techniques such as Bayesian structural time series and uplift modeling.
- Familiarity with time series forecasting, supply chain optimization, or related domains.
Responsibilities
- Design, implement, and productionize causal inference methodologies to quantify the incremental impact of product changes, marketing campaigns, and operational interventions.
- Apply techniques including (but not limited to) double machine learning, instrumental variables, propensity scoring, structural time series, and synthetic control methods.
- Conduct empirical investigations to guide experimentation strategy and develop frameworks for decision-making under uncertainty.
- Contribute to building Keystone's internal libraries for causal estimation and validation.
- Work closely with product managers, economists, data scientists, and ML engineers to integrate causal frameworks into existing workflows, ensuring that model outputs are actionable and aligned with business goals.
- Stay current with research in causal inference and apply novel techniques where appropriate.
- Ensure that causal models are interpretable, statistically valid, and operationally reliable.
Other
- PhD in Economics, Statistics, Computer Science, or a related quantitative field.
- 5+ years of professional experience with applied science, econometric modeling, structural economic analysis, or statistical modeling in practical business applications.
- Familiarity with supply chain processes (such as demand planning, S&OP and inventory optimization) and/or commercial processes (such as marketing measurement, personalization and targeting).
- Excellent communication skills, capable of conveying complex technical concepts clearly to both technical and non-technical stakeholders, including executive-level audiences.
- Demonstrated ability to collaborate with cross-functional stakeholders, including finance, product, and operations, to drive adoption of causal results in strategic decision-making.
