Software Engineer, Pricing MLOps

The Pricing team is the engine behind Opendoor’s ability to price homes with speed, scale, and confidence. We build the core platform that turns data, models, and business logic into the prices that power our entire business. Our services and data infrastructure are mission‑critical to pricing decisions and automation, and they must be fast, accurate, and resilient—because even small improvements can drive major business impact. We’re looking for a senior‑level Software Engineer to join our Pricing & ML team, leading the design and evolution of the platform and tooling that productionize the machine learning models behind our pricing engine. This role is ideal for an engineer who enjoys working close to data and models, has meaningful experience with ML workflows, and wants to shape technical direction as well as ship high‑impact systems. Our models are pragmatic and straightforward—we prioritize value, reliability, and iteration speed over complex research systems. In this role, you’ll work side‑by‑side with backend software engineers, data scientists, ML engineers, product managers, and partner engineering and operations teams to turn prototypes and ideas into robust, scalable, and observable production systems. You’ll own high‑impact initiatives end‑to‑end, mentor other engineers, and have significant influence over how our pricing platform evolves and how we shape the future of real estate. What You’ll Do Lead the design and implementation of services, tooling, and workflows that enable reliable training, deployment, and monitoring of pricing and ML models Work closely with researchers and analysts to convert model prototypes into clean, testable, production‑ready Python code and systems Own and operate model pipelines end‑to‑end — including data ingestion, training, validation, versioning, deployment, and monitoring Design and maintain workflows that support the full ML lifecycle: experimentation, training, evaluation, deployment, and iteration Develop and optimize data access patterns and SQL queries over large, complex datasets Implement robust automation for key ML lifecycle workflows (e.g., scheduled retraining, rollbacks, A/B tests, canary releases) Drive improvements in reliability, observability, performance, and cost‑efficiency across ML pipelines and model‑serving environments Proactively address real‑world challenges like data drift, model decay, and changing market conditions in the real estate domain Contribute to and help define shared ML infrastructure, patterns, and best practices across the Pricing & ML team Lead code reviews and technical design discussions; mentor and support other engineers on ML‑adjacent work Participate in and help improve on‑call and incident response processes for ML systems What You’ll Need 8+ years of experience in software engineering or 6 years with a Masters or ML engineering, including substantial work with ML‑adjacent or production ML workflows Strong proficiency in Python, with a track record of writing maintainable, modular, and well‑tested production code Solid experience working with SQL (queries, joins, indexing, and performance optimization) Proven experience owning and operating data pipelines and/or model training/serving pipelines in production or high‑stakes environments Deep familiarity with the end‑to‑end ML lifecycle (training, evaluation, deployment, monitoring, and iteration) Demonstrated ability to make and communicate technical design decisions and tradeoffs across multiple stakeholders Strong collaboration and communication skills, especially when working with data scientists, researchers, and cross‑functional partners A bias toward impact, learning, and pragmatic solutions in a fast‑moving, high‑stakes domain Focus ML infrastructure and operations rather than model research. Building, deploying, and maintaining ML pipelines and systems. All roles are expected to be hands‑on coding roles. All MLOps roles are expected to be Seattle‑based. Nice to Have Experience working on ML systems in business‑critical environments (e.g., pricing, forecasting, logistics, marketplaces, risk) Familiarity with ML ops concepts and tools (e.g., model serving frameworks, feature stores, experiment tracking, model registries) Experience with tools such as MLflow, Airflow, Spark, or Delta Lake Experience monitoring model performance in production (e.g., drift detection, quality alerts, dashboards) Experience with streaming / event‑driven systems (e.g., Kafka) or scheduling/orchestration tools Comfort working in a Linux‑based, cloud‑hosted environment (e.g., AWS) Interest in real estate or other messy, high‑stakes domains with imperfect data #J-18808-Ljbffr Cacheflow