Data Scientist - Inference, Safety and Customer Care

About the role

You own the design, execution, and interpretation of causal inference studies that directly shape high-stakes product and policy decisions in Safety and Customer Care. You will translate ambiguous operational questions into rigorous experimental and quasi-experimental strategies, ensuring that every intervention is measured with scientific rigor. You own the end-to-end analytical lifecycle, from hypothesis formulation and model development to stakeholder communication and decision advocacy. You partner as a core member of a multidisciplinary team, aligning data insights with product, design, engineering, and operations priorities. You are responsible for building causal ML models that optimize concession budget allocation and maximize trust across rider and driver communities. You quantify long-term effects of support experiences on retention while uncovering heterogeneous treatment effects across diverse user segments. You ultimately empower data-driven culture within SCC by turning complex evidence into clear, actionable recommendations for leadership.

Key facts

What you'll do

Define and lead rigorous causal inference projects that measure the impact of SCC products, AI-agent launches, and operational interventions.

Design and implement robust evaluation frameworks using randomized controlled trials and quasi-experimental methods to support data-informed launch decisions.

Construct causal ML models to optimize concession budget allocation, targeting the right support credit to the right rider or driver at the right moment.

Quantify long-term effects of support-experience changes on rider and driver retention across multiple time horizons.

Uncover heterogeneous treatment effects to understand how interventions perform across different communities, behaviors, and contexts.

Deliver strategic insights on quality-cost tradeoffs that enable leadership to balance service quality, coverage, and operational cost at scale.

Collaborate cross-functionally with product, design, engineering, operations, and analytics to co-create solutions and drive innovation.

Communicate findings clearly and compellingly to both technical and non-technical audiences, fostering a culture of evidence-based decision-making.

Develop reusable methodologies and tools that elevate the standard of causal analysis across the SCC organization.

Think strategically about scaling data science capabilities within SCC to support long-term platform outcomes and evolving business needs.

Champion best practices in model lifecycle management, from feature engineering through production deployment and monitoring.

Identify and prioritize opportunities where causal insights can de-risk major initiatives and unlock new value for riders, drivers, and the company.

Partner closely with operations leaders to integrate data insights into support workflows, credit allocation, and quality assurance processes.

Maintain a bias toward impact by converting analytical findings into concrete recommendations that drive measurable business and trust outcomes.

Requirements

2+ years of industry experience in causal inference or data science with a Master's degree in a quantitative field (statistics, economics, computer science, etc.), or a PhD in a relevant field.

Strong knowledge of causal inference and experimental design, including core concepts such as confounding, randomization, and identification strategies.

Experience with uplift modeling / heterogeneous treatment effect (CATE) estimation using both parametric and non-parametric approaches.

Proven ability to apply statistics to unstructured problems and deliver measurable results in fast-paced, ambiguous environments.

Expertise in SQL and experience with large-scale data platforms such as Hive, Spark, or similar distributed systems.

Proficiency in Python and working within production coding environments, including data wrangling, model development, and integration workflows.

Excellent project management, communication, and collaboration skills to coordinate with multiple stakeholders and timelines.

Experience partnering with operational teams and support systems, including customer care workflows, agent operations, or credit budget allocation.

Clear understanding of ethical considerations in modeling and decision-making, with attention to fairness, bias, and transparency.

Nice to have

Experience working with AI/LLM applications, including LLM-powered agents, retrieval systems, or evaluation frameworks.

Practical notes

This role is based in Toronto, Canada. Engagement type is See source. No additional hours, travel, visa, or deadline information is provided beyond what is stated in the source text.