Sprawlanalytics is an AI-native software company building portfolio intelligence tools for commercial real estate. Our analytics engine processes thousands of lease records in seconds, surfacing geo clustering, expiration risk, cost benchmarking, and AI-powered segmentation — all server-side, all real-time.We're growing and looking for a Mid-Level Data Scientist to own the intelligence layer of everything we build.What You'll OwnThe analytics engine: maintain, extend, and optimize our pure-Python data pipeline that powers portfolio insightsAI/ML models: build and ship clustering, segmentation, forecasting, and optimization models into productionWebsite & product data: track, analyze, and improve how users interact with the platform — from funnel metrics to feature adoptionData quality: design validation pipelines so every insight we surface is one a customer can trustExperimentation: run A/B tests, measure impact, and translate results into product decisionsWhat We're Looking For2 to 5 years of experience in data science or a closely related roleStrong Python skills (pandas, NumPy, scikit-learn, machine learning, — our stack, not a nice-to-have)Hands-on experience building and deploying ML models, not just notebooksComfort working across the full pipeline: raw data in, production insight outClear communicator — you can explain a k-means result to an engineer and a product decision to a founderSelf-directed: we're a lean team, you'll own your work end to endBonus if you have:Experience with geospatial data or real estate datasetsFamiliarity with Flask or similar Python web frameworksBackground in SaaS analytics or product dataWe're fully remote. You bring the focus, we bring the problems worth solving.

Data Scientist (Remote, Full-Time)

Emma

Requirements and responsibilities

Skills wanted:

Language(s) required:

sprawlanalytics.com

Admin access needed