Metropolis · posted · checked
Staff Machine Learning Engineer, Growth
AirflowAWSPythonSparkSQL$220k – $260kOn-site · SeattleStaff+
Who can apply
On-site · Seattle
Location: Seattle, Washington, United States
Who we are
The real world is the next frontier, and at Metropolis, we are creating artificial intelligence to make it responsive. We are pioneering the Recognition Economy — a future where mundane repetition disappears and being known unlocks access, comfort, and belonging everywhere you go. From transforming parking into a seamless drive-in, drive-out experience for millions of Members to expanding our intelligence layer across retail and hospitality, we are building a world that feels instinctive and magical. The future isn't coming; it's here, and we need builders, innovators, and problem solvers to help us create it.
Who you are
Metropolis is seeking a Staff Machine Learning Engineer to build and scale our demand forecasting and dynamic pricing systems within the Advanced Technology Group. In this highly impactful role, you will design, deploy, and own end-to-end models that forecast demand, capture price-demand relationships, and use causal inference and double ML to create actionable pricing strategies. You will collaborate closely with product, engineering, and business teams to translate complex requirements into scalable machine learning solutions that directly drive key metrics such as revenue, utilization, and customer demand.
What you'll do
Lead the innovation, design, and advancement of machine learning and mathematical optimization solutions to maximize revenue and improve business performance.
Be a technical thought leader on cutting-edge pricing topics and closely follow industry and academic trends.
Drive technical best practices and raise the technical/operation bar for Metropolis Growth ML team.
Design and implement advanced frameworks, including constrained optimization, mixed-integer programming, and stochastic optimization, to drive scalable pricing decisions
Architect and productionize scalable demand forecasting models optimized for business goals like visit volume, revenue maximization, and inventory availability
Build and deploy end-to-end data pipelines to support large-scale production usage
Identify data issues including bias, leakage, and labeling inconsistencies, and drive solutions