We are seeking a statistically rigorous and operationally pragmatic analyst to close the gap between what the causal model infers from historical data and what controlled evidence can confirm. This individual will move the organization from wide-interval estimates based on observational data alone toward narrow, confident causal effect estimates grounded in designed experiments run in live operational environments.
This individual will partner closely with the Senior Data Scientist, Data Engineers, the Technical Product Manager, and operations teams across Personal Wealth to prioritize experiments, implement randomization safely in live service environments, and feed results back into the model in a structured, auditable way.
The role requires strong experiment design skills, comfort with both frequentist and Bayesian inference, hands-on experience instrumenting logging pipelines, and the operational judgment to run experiments that are statistically sound without disrupting the service environment they are designed to study.
Key Responsibilities Experiment Prioritization & Design - Identify which causal relationships in the model carry the most uncertainty and build a prioritized experiment roadmap that resolves the highest-value gaps first
- Design operational experiments end-to-end: randomization strategy, unit of randomization, sample size and power calculations, guardrail metrics, and pre-registered analysis plan
- Distinguish between interventions that can be randomized directly and situations that require natural experiment or quasi-experimental methods - and design accordingly
Instrumentation & Execution - Instrument experiment logging infrastructure: treatment assignment, exposure windows, and outcome collection pipelines that produce clean, analysis-ready data
- Work with operations teams to implement randomization safely - maintaining experimental integrity without disrupting service commitments or creating inequitable client experiences
- Identify and exploit natural experiments (outages, weather events, system changes, policy shifts) as additional sources of causal evidence when designed experiments are not feasible
Analysis & Model Integration - Analyze experiment results and produce causal effect estimates with confidence intervals formatted for ingestion into the causal model
- Partner with the Senior Data Scientist to translate experiment outputs into Bayesian model updates - narrowing confidence intervals on the levers that matter most to planning decisions
- Communicate results clearly to non-technical operations and CX stakeholders, distinguishing between statistically significant findings and inconclusive results
Experiment Registry & Institutional Knowledge - Maintain a structured registry of completed experiments, effect estimates, confidence intervals, and methodology notes - the institutional memory of what the organization has learned about its own operations
- Establish standards for experiment documentation so findings are reproducible, auditable, and usable by future analysts
- Proactively share findings with analytics and business partners to inform decisions beyond the immediate modeling context
Qualifications - Undergraduate degree or equivalent combination of training and experience required. Graduate degree in statistics, economics, or a related quantitative field preferred.
- Minimum of four years of experimentation or applied statistics work, with demonstrated experience designing and analyzing experiments in operational or business settings.
- Strong experiment design skills: power analysis, randomization strategies, variance reduction techniques (CUPED, stratification), and interference handling.
- Proficiency in Python or R for statistical analysis.
- Familiarity with both frequentist and Bayesian approaches to inference.
- Hands-on experience with logging and instrumentation - exposure tables, treatment assignment pipelines, and outcome tracking.
- Experience with operational experiments (staffing, routing, queue management) rather than purely digital product tests preferred.
- Familiarity with causal inference methods and the relationship between experimental and observational evidence preferred.
Special Factors Sponsorship Vanguard is not offering visa sponsorship for this position.
About Vanguard At Vanguard, we don't just have a mission-we're on a mission.
To work for the long-term financial wellbeing of our clients. To lead through product and services that transform our clients' lives. To learn and develop our skills as individuals and as a team. From Malvern to Melbourne, our mission drives us forward and inspires us to be our best.
How We Work Vanguard has implemented a hybrid working model for the majority of our crew members, designed to capture the benefits of enhanced flexibility while enabling in-person learning, collaboration, and connection. We believe our mission-driven and highly collaborative culture is a critical enabler to support long-term client outcomes and enrich the employee experience.
Never miss an opportunity! Create an alert based on the job you applied for.
