Applied Scientist

Opendoor•Toronto, ON

10h

About The Position

We’re looking for an Applied Scientist to work on some of the hardest quantitative problems at Opendoor. This role will focus primarily on structural modeling, econometrics, optimization, and decision-making under uncertainty, with applications spanning pricing, resale strategy, demand modeling, and risk management. This role will contribute to our broader valuation and pricing ecosystem and we’re looking for someone who can combine strong modeling intuition with hands-on execution and strong engineering to build practical solutions for a low-margin, high-stakes business where small improvements can have an outsized impact. You’ll work on problems like modeling post-listing demand, estimating price elasticity, designing experiments, building structural models, and developing optimizers that help us make better decisions across our products and inventory. We’re a small, nimble team, so there’s ample opportunity to shape both the modeling direction and how these systems get used in production decision-making.

Requirements

Experience developing quantitative models to support real-world decision-making under uncertainty
Strong coding skills in Python, with the ability to move beyond prototyping and implement production-quality scientific code
Experience with one or more of the following: causal inference, Bayesian modeling, structural modeling, demand forecasting, pricing science, or mathematical optimization
Comfort working with messy, high-dimensional real-world data and translating ambiguous business problems into rigorous modeling approaches
Advanced degree (MS or PhD preferred) in statistics, mathematics, economics, operations research, computer science, or another quantitative discipline
Strong communication and collaboration skills — you’re comfortable working with cross-functional stakeholders and can communicate technical ideas clearly

Nice To Haves

Experience in pricing, marketplace modeling, revenue management, supply/demand systems, inventory optimization, or risk modeling
Background in real estate, housing, finance, or adjacent marketplace domains
Familiarity with distributed data processing tools such as Pyspark
Experience with machine learning methods broadly, including where deep learning can complement structured statistical modeling
Experience working with large language models (LLMs) or vision-language models (VLMs)

Responsibilities

Build models that help Opendoor make better decisions around pricing, resale strategy, and portfolio risk
Develop demand and conversion models using both pre-listing and post-listing signals
Design and improve optimization frameworks that balance objectives like margin, conversion, and risk
Apply statistical, econometric, and mathematical modeling techniques to problems where structure matters and pure black-box prediction is not enough
Design experiments and measurement approaches to quantify price elasticity, customer response, and product trade-offs
Partner with Engineering, Product, and Operations to turn models into systems that influence real decisions
Bring a pragmatic, hands-on approach: move quickly from idea to prototype to production-ready scientific component