Lead Data Scientist

Job Description

As Lead Data Scientist, you will define and execute the analytics and predictive data roadmap for SmartRent’s next-generation offerings, starting with decision-support models and machine learning for optimal property operations. You will spearhead the model development lifecycle from stakeholder collaboration to deployment within a Databricks environment.

Reporting to the SVP of Enterprise Data and AI in our new and transformational organization, you will combine quantitative rigor with practical problem-solving to deliver measurable value to internal and external stakeholders. You will partner with Data, AI, Product, and Engineering peers to solve our most complex challenges.

Responsibilities

• Frame business problems with Product and Revenue partners and turn them into modeling approaches with clear success metrics.
• Create compelling data visualizations that support insightful story telling and inform the design of predictive models.
• Build machine-learning models on large-scale time-series telemetry, including anomaly detection, failure prediction, and time-to-event models.
• Develop clean, well-documented code that promotes reuse and drives operational efficiency within the organization.
• Ship models to production on Databricks, and support their quality after launch: monitoring, diagnosing drift, and retraining.
• Partner with Engineering to scale and harden production workloads.
• Design experiments and impact analyses that tie model performance to customer and revenue outcomes.
• Set modeling standards and documentation practices for a growing team.

Required Qualifications

• Bachelor's degree in Computer Science, Mathematics, Statistics, Engineering, or a related quantitative field; or equivalent professional experience.
• 7+ years in data science, with a track record of models running in production that customers or products relied on.
• Deep expertise in time series, anomaly detection and ensemble modelling methods.
• Hands-on experience wrangling and modelling data in Databricks, plus platform capabilities like feature stores and experiment management.
• Advanced usage of SQL and Python to organize large, complex datasets.
• Strong proficiency in experiment design and causal or impact measurement.
• Passion for communicating and presenting technical concepts to non-technical audiences.

Preferred Qualifications

• Experience with applying LLMs within data science workflows, such as feature extraction from unstructured data, LLM-assisted analysis, or evaluating generative outputs.
• Experience enabling self-service data access in Databricks using features such as AI/BI Dashboards and Genie.
• Exposure to deploying machine learning pipelines end-to-end including implementing MLOps best practices. 
• Experience in proptech, real estate technology, IoT, or SaaS platform environments.
• Familiarity with Git-based version control and Terraform.