Data Scientist

Responsibilities

• Real Estate Market Modeling:
  Build models applied to challenges such as valuation/pricing leveraging techniques from classic supervised ML to more advanced approaches.
• Multimodal Embeddings:
  Create vector representations of Real Estate entities, such as listings, combining images, text, and structured attributes to power search, matching, deduping, or recommendations.
• Data Analysis & Experimentation:
  Use SQL/Python to extract, clean, and analyze data; design experiments and evaluate model-product impact with robust metrics.
• Model Operationalization:
  Ship models to production with capabilities such as monitoring, automated rollout, or CI/CD (in partnership with engineering).
• Cross-functional Delivery:
  Partner with product, engineering, and operations teams to translate business problems into scalable ML solutions.

• Proven Experience:
  
  4–8 years in applied data science/ML, delivering models that move real-world KPIs.
• SQL & Python Mastery:
  Strong in frameworks such as Pandas/Num Py/Scikit-learn...building reliable data pipelines, model training and evaluation.
• MLOps Fundamentals:
  Experience deploying/maintaining models (batch or real-time), versioning, CI/CD basics, observability, and reproducible training.
• Communication & Ownership:
  Clear with technical/non-technical stakeholders; can scope, prioritize, and explain tradeoffs.
• Comfortable with uncertainty, data quality issues, leakage risks, and market dynamics (location, seasonality, inventory shifts).
• Nice to Have:
  Software engineering experience; multimodal/vision experience; voice AI (ASR/NLU) exposure.
• Academic Background:
  Bachelor’s in STEM (Master’s a plus).