Senior Data Scientist


New York City, New York, United States, NY

New York City, New York, United States, NY, US
New York City, New York, United States, NY
30+ days ago


Technology underpins our entire business. From modernizing our systems, simplifying our technology environment, to developing industry-shaping tools, technology allows us to connect with and serve our clients, reduce risk and create business opportunities with cutting-edge products. At Sotheby’s we use data science to unravel the secrets of art and luxury commerce space. This enables us to efficiently scale the marketplace business for our clients. In this role, you will utilize a unique set of data to model rich dynamics critical for business functions. You will work in a team of data engineers, machine learning engineers, infrastructure engineers, and product managers to build and deliver data science products that unlock supply and predict demand in the Sotheby’s marketplace.


  • Work on the end-to-end data science pipeline: from data collection and cleaning, to experimenting with predictive models, to deployment of the results
  • Perform exploratory data analysis and write data pipelines to improve data quality for downstream tasks
  • Develop and train feature extraction models for unstructured commerce data pertaining to art and luxury collectibles, using deep learning models
  • Design, build, and iterate on a unified deep learning model architecture, using an autoencoder, to learn representations for all art and luxury commerce items
  • Train models to understand and predict price dynamics of artworks and other luxury commerce categories
  • Build recommender systems for artworks and other luxury commerce categories, to deliver a highly personalized experience to clients
  • Develop off-line evaluation metrics and craft real-world tests to measure model’s efficacy
  • Build production data pipelines and services on Google Cloud Platform to deploy data science products
  • Contribute to the product vision for reshaping a 300-year old industry through automation and data science


  • Bachelor’s degree in a quantitative field or equivalent experience
  • M.S. in CS, EE, Stats or other quantitative field; Strong understanding of statistics and machine learning a plus
  • 2+ years of experience working with and designing machine learning/deep learning models
  • 2+ years of experience developing production data pipelines and machine learning services
  • Highly proficient programming for data engineering and data science: either Python, C++, or Java. (3+ years of experience in Python preferred)
  • Experience with ML tools such as: Tensorflow, pytorch, scikit-learn; data processing technologies such as: Apache Beam, Google Cloud Dataflow
  • Collaborative, solution-oriented and with the ability to multi-take on a lean team


About the Company