×

Data Scientist

Who we are

BlueSuit unlocks data hidden in unstructured real estate documents to superpower our customers’ insights, productivity, and workflow. Our API-forward data extraction company was founded in late 2018, and our API launched with customers in 2021.

We are looking to add a key data science team member to help drive customer value. Our team is made of successful prior founders, data, and real estate industry professionals & we proudly attended the Colliers-Techstars Proptech accelerator in 2019.

The Role

As an early member of our Data Science team, you will help build our machine learning platform that drives our document extraction products – both contributing to existing efforts in collaboration with your team members, as well as taking ownership of new projects.

You’ll succeed in this role as a creative problem solver who thrives in a dynamic, early-stage environment.  You’re comfortable experimenting and prototyping to discover the most impactful solutions, constantly balancing evolving short-term business priorities and early market validation with long-term strategic objectives.  

Active and transparent communication among internal stakeholders with an eye for early customer value will be key to your success as BlueSuit’s platform approaches scale.

Responsibilities will vary and include the opportunity to evolve as the company grows.  

Current Expectations

  • Coordinating with BlueSuit heads of product and user experience to scope and deliver on data science objectives by participating in agile rituals to meet business needs.
  • Leading one or more document data extraction projects on BlueSuit’s product road map & becoming the Data Science team’s resident Subject Matter Expert on these documents.
  • Training machine learning models, encompassing vision, text & tabular data, to deploy as part of software pipelines capable of extracting key data from these highly unstructured documents. 
    • Current ML frameworks utilized by our Data Science team include fastai, HuggingFace, GPT-3, TensorFlow’s Object Detection API, scikit-learn & spaCy – you will be encouraged to utilize these but also research, experiment with & implement other open source options.
  • Be flexible & creative as you craft bespoke pipelines for each document. 
    • While you will be able to borrow from the Data science team’s existing suite of tools, techniques & models (our Document Agnostic Extraction Platform) – there is unlikely to be a cookie-cutter solution. Each project you work on will include unique elements of data sourcing (which you will help coordinate with BlueSuit’s labeling team), data scrubbing, feature engineering – and you will likely find the best results are achieved combining not only machine learning models in your pipeline, but also heuristics based on on your developed Subject Matter Expertise.
  • Contribute back to the Data Science team’s Document Agnostic Extraction Platform through code and robust documentation of your findings to help power future product developments.
  • Work with Engineering to deploy your model pipelines into production. 
    • Our data scientists don’t just train models, they build software pipelines to utilize them, so they are comfortable with basic engineering concepts & responsibilities.

Preferred Qualifications

  • 3+ years working as a Data Scientist with a focus on machine learning
  • Experience writing maintainable, testable, production-grade Python code
  • Comfortable working both as an individual contributor as well as part of a highly collaborative team
  • A broad based knowledge across various machine learning modalities – including computer vision (e.g. object detection), natural language processing (e.g. NER) & tabular data (classification & regression)
  • Experience working with a range of machine learning frameworks. 
    • The specific technologies (like those mentioned in the responsibilities section above) are less important than an ability to quickly learn and prototype with a new framework
  • The ability to achieve robust machine learning results with limited data
  • Experience working with version control (e.g. git/Github)
  • Bonus areas of experience:
    • AWS (or other cloud provider)
    • Docker
    • Bash scripting
    • CI/CD

Salary & Benefits

BlueSuit is based in Denver, Colorado in the Lower Highlands neighborhood, just west of Downtown.

  • Annual compensation: $130,000 – $170,000 (Dependent on experience, with opportunity for equity) 
  • In-office and/or remote work options
  • RTD Passes
  • 401k
  • Healthcare coverage: Medical, Dental, Vision
  • Unlimited PTO
  • Relocation support available if desired

Interested?