Data Scientist

Job Description

As a Data Scientist at SmartRent, you will work at the intersection of our property technology platform and advanced analytics, transforming complex IoT telemetry, resident behavior signals, and operational data into models and decision-support tools that improve outcomes for operators, residents, and SmartRent's internal teams. You'll build and deploy production-grade machine learning solutions, partnering closely with Data Engineering, Product, and business stakeholders to bring models from experimentation through to live product features.

Our Data & Analytics team, part of our new transformational Data and AI organization sits at the center of this ecosystem, transforming data into intelligence that powers SmartRent products and drives value for our customers.

 

Responsibilities

• Design, build, and validate supervised and unsupervised ML models (classification, regression, clustering, recommendation systems) tied directly to SmartRent product and operational use cases such as predictive maintenance for IoT devices, resident churn prediction, and smart access anomaly detection.
• Work within the Databricks platform: build and manage ML workflows for experiment tracking, Delta Live Tables for feature pipelines, and Unity Catalog for governed access to SmartRent's property and device datasets.
• Conduct exploratory data analysis, feature engineering, and statistical hypothesis testing across SmartRent's structured and semi-structured data sources including device telemetry, resident events, leasing data, and support interactions.
• Develop and maintain predictive analytics solutions that directly inform SmartRent product features and operator decision-making, including capacity planning tools and resident experience scores.
• Monitor deployed model performance, retrain as needed, and document model drift and remediation actions maintaining production reliability for models surfaced in SmartRent's operator and resident-facing applications.
• Collaborate with Data Engineering to integrate ML solutions into SmartRent's data platform and downstream product surfaces.
• Partner with Software Engineering to move models from experimentation into production APIs and embedded product features.
• Develop clean, well-documented, and reusable code following engineering best practices contributing to shared libraries and ML tooling used across the analytics organization.
• Partner with Product and business stakeholders to translate business problems (e.g., optimizing unit turn times, predicting lease renewal likelihood) into precise analytical questions.
• Present findings, model outputs, and recommendations to non-technical audiences including senior leadership.
• Contribute to data governance, data quality standards, and related documentation within our data environment.
• Respond to ad hoc analysis requests and help build a culture of data-driven decision-making across SmartRent.

 

Required Qualifications

• Bachelor's degree in Computer Science, Mathematics, Statistics, Engineering, or a related quantitative field; or equivalent professional experience.
•  3+ years of hands-on experience in a data science or quantitative analytics role.
• Strong programming proficiency in Python, including experience with production-grade codebases (PySpark experience a strong plus).
•  Proven experience training and evaluating supervised and unsupervised ML models.
•  Advanced SQL skills; comfort working with large, complex, and disparate data sources including event-based and time-series data..
• Experience with Databricks or equivalent cloud-based lakehouse / big data platforms (Spark, Delta Lake).
• Experience with NLP techniques including text preprocessing, entity recognition, and sentiment analysis.
•  Familiarity with standard data formats: CSV, JSON, XML, Parquet, etc.
•  Strong written and verbal communication skills with demonstrated ability to present technical results to non-technical stakeholders.

 

Preferred Qualifications

• Master's degree or higher in a quantitative discipline.
• Hands-on experience with Databricks ML features: MLflow, Databricks AutoML, Feature Store, Model Serving, and Delta Live Tables.
• Experience in proptech, real estate technology, IoT, or SaaS platform environments.
• Familiarity with IoT data patterns: time-series telemetry, device state machines, event stream processing.
• Experience building recommender systems or personalization engines applicable to resident or operator-facing products.
• Exposure to model risk management frameworks or ML governance practices, including model cards and lineage tracking.
• Experience working with Snowflake data platforms.
• Experience working directly with executive or senior leadership stakeholders.