MINIMUM QUALIFICATIONS:
- Master's degree in a quantitative discipline such as Statistics, Engineering,
Sciences, or equivalent practical experience.
- 4 years of experience in data science with a specific focus on time series
analysis and forecasting.
- Experience with Python or R programming with relevant forecasting libraries.
- Experience in causal inference, A/B testing, statistical modeling, or machine
learning.
- Experience with a range of forecasting methods, from classical statistical
models to machine learning approaches.
PREFERRED QUALIFICATIONS:
- PhD degree in a relevant quantitative field.
- 6 years of experience deploying and maintaining forecasting models in a live
production environment.
- Experience with recent advancements in forecasting, such as foundation models
(TimesFM) or deep learning approaches.
- Experience in a demand planning, contact center, or operational workforce
management role.
- Familiarity with cloud platforms (preferably Google Cloud Platform) and their
AI/ML services (e.g., BigQuery, Vertex AI).
- Ability to apply judgmental forecasting and incorporate qualitative business
adjustments into model outputs, especially for new or unprecedented events.
ABOUT THE JOB:
In this role, you will develop and maintain forecasting models that predict
customer support case volume. Your work will directly inform staffing,
budgeting, and planning decisions, enabling the delivery of exceptional customer
support at scale.
RESPONSIBILITIES:
- Develop, deploy, and maintain time series forecasting models to predict
customer support case volumes across various products, regions, and channels.
- Build and automate scalable data pipelines to ensure timely and reliable data
for model training and inference.
- Monitor and evaluate model performance continuously, tracking key accuracy
metrics, identifying model drift, and ensuring forecast reliability, and
researching and implementing state-of-the-art forecasting techniques to
continuously improve model accuracy and capabilities.
- Partner with Operations, Finance, and leadership stakeholders to understand
their planning needs, deliver forecasts, and explain variance drivers.
- Communicate forecast results and uncertainty to both technical and
non-technical audiences to guide decision-making.
