Scientific Software Developer

Location: Boston, MA

Department: Science

Type: Full Time

Min. Experience: Mid Level

Company Overview

True Fit is a data-driven platform that uses one-of-a-kind data to help people find clothes and shoes that they love and keep. We have the world's most complete fashion dataset allowing us to connect consumers, brands, and retailers across the entire industry.  This dataset is the fuel for deep personalization powered by machine learning and driven by our Science and Engineering teams. We are looking for an energetic and motivated Scientific Software Developer to join us at our downtown Boston location.

 What we do

  • Combine data from disparate sources into a universal fashion retail database so that data is connected seamlessly across our network of brands and retailers.
  • Leverage this data for collaborative filtering, text analysis, anomaly detection, and more.
  • Train large models in scalable frameworks with our massive data set consisting of millions of users, products, and related transaction data accounting for billions of dollars of online sales.
  • Serve low latency recommendations with software that can scale to support huge retailers during the holidays. 

What you will do

  • Participate in the development and prototyping of new analytic products to help consumers find apparel and footwear that fits and flatters them.
  • Build new tools and services to support these new analytic products in a cloud computing environment.
  • Implement large-scale machine learning algorithms in a scalable framework, e.g. Spark.
  • Work with the rest of the Data Science team to develop at-scale prototypes of new and/or improved products and measure their real-world performance.
  • Work with the Development Team to assist with moving the prototypes to production, verifying production performance, and maintaining a path for further innovation and performance measurement over the life of the product.
  • Participate in production code reviews.

Required Experience/Skills

  • Education and/or experience in a quantitative field. (Bachelor’s degree or equivalent work experience).
  • 3-5 years professional experience with at least one year at an organization producing solutions based on analysis of large data sets.
  • Knowledge or experience in implementing large-scale machine learning training and prediction pipelines in a production environment.
  • Experience with Python or Scala (or both) and a willingness to learn and use the other where required.
  • Strong SQL skills.  Experience with SparkSQL or Hive is a plus.
  • Experience with at least one of the major big data tools and frameworks (e.g. Hadoop, Pig, Spark). Experience with Spark is a plus.
  • Able to manage and juggle involvement in multiple priorities and projects.
  • Excellent English communications skills.
  • Ability to rapidly learn new tools as they become needed.

We are proud to foster a workplace free from discrimination. We strongly believe that diversity of experience, perspectives, and background will lead to a better environment for our employees and a better product for the brands, retailers, and users that we work with. This is something we value deeply and we encourage everyone to come be a part of the digital revolution of fashion retail. 

Forward this Position
Recipient email address (one)
Your name
Your email address
Enter a message (optional)
Human Check*
Apply for this Position
* Required fields
First name*
Last name*
Email address*
Phone number*

Attach resume as .pdf, .doc, or .docx (limit 2MB) or paste resume

Paste your resume here or attach resume file

Cover Letter*
Who referred you to this position?
What’s your citizenship / employment eligibility?*