What You’ll Do

• Build pipelines for place and location-related data.

• Work with noisy real-world signals and large geospatial datasets.

• Improve quality, reliability, and observability of derived datasets.

• Define metrics and feedback loops for data quality and attribution.

• Prototype in Python, SQL, notebooks, or similar tools.

• Integrate scoped production experiments with amo’s backend systems.

• Run offline evaluations and A/B tests where relevant.
  
  

Must Have

• Strong Python and SQL.

• Production experience with Python or Scala.

• Experience with PySpark, Spark SQL, Spark Streaming, Parquet, and Iceberg.

• Experience with large datasets and data pipelines.

• Experience with geospatial data, POI datasets, place matching, or similar real-world entity data.

• Comfort with metrics, experimentation, and data quality measurement.