hybrid
Staff Causal Inference Scientist
Staff Causal Inference Scientist
As a Staff Causal Inference Scientist on the Rider New Product team, you will drive innovation by applying advanced causal inference techniques to rigorously measure the incremental impact of new product features for millions of riders. You will own complex measurement problems, lead high-impact initiatives, and build production-grade causal models, directly shaping the future of Lyft's rideshare experience and growth strategy.
About the role
About the Role
The Rider New Product team at Lyft is dedicated to innovation and rigorously quantifying the value of new features. As a Staff Causal Inference Scientist, you will play a critical role in unlocking Lyft’s next generation of growth by applying advanced causal inference to measure the true incremental impact of new product features. This is a high-impact, highly technical position where you will leverage your expertise in applied causal inference, advanced measurement techniques, and production-grade coding to shape critical business decisions and bridge the gap between cutting-edge research and product impact.
Responsibilities
- Own complex, open-ended incrementality measurement problems, translating ambiguous product launches into concrete causal frameworks and experimental designs.
- Lead high-impact Causal Inference initiatives, driving innovation by introducing advanced measurement techniques to quantify the incremental impact of new rider features.
- Partner deeply with Product, Engineering, and Finance to define the technical vision for how Lyft evaluates innovation, moving beyond simple correlations to understand long-term drivers of rider behavior and value.
- Design and build production-grade measurement systems, developing and deploying robust causal models pipelines that balance high scientific rigor with practical constraints.
- Establish robust evaluation frameworks to ensure the "engine of innovation" steers the business toward sustainable, incremental growth.
- Build reusable science infrastructure, creating internal libraries and best practices for causal discovery and automated measurement.
- Mentor and guide junior/mid-level scientists, serving as a technical advisor on experimental design, statistical modeling, and fostering a culture of scientific excellence.
Experience
- Advanced Quantitative Background: Master’s or PhD in Economics, Statistics, Applied Math, Computer Science or equivalent high-impact industry experience.
- 3+ Years of Applied Experience: Proven track record in applied science or data science, with a focus on deploying causal models that drive measurable business outcomes.
- Deep product intuition and hands-on experience with causal methods.
- Strong proficiency in Python and SQL.
- Experienced in defining and executing sophisticated evaluation strategies, including advanced experiment design and counterfactual analysis to isolate incrementality.
- Proven ability to align cross-functional partners, influence technical architecture, and challenge scientific assumptions to guide high-level product strategy.
- Excellent ability to articulate complex causal concepts, trade-offs between rigor and speed, and scientific findings to both technical peers and executive stakeholders.
Preferred Qualifications
- Demonstrated ability to own high-stakes, open-ended problem spaces, translating vague business questions into rigorous scientific roadmaps.
- Experience in mentoring other scientists, elevating the bar for technical quality, and establishing best practices for modeling and scientific reasoning.