Senior Data Scientist

At Quant

AQ, we envision a world in which actionable air quality information is available and accessible. To build that future, we must bring every skill set to the table, working collaboratively across disciplines and fields. If this excites you, read on!

As a company, we value the role fundamental scientific and engineering research play in developing new technologies while acknowledging that what we do must scale.

At Quant

AQ, we design and manufacture professional-grade air quality sensors for a variety of customer types (including research, government, and the private sector) to enable informed decision-making. We provide our customers with everything they need to build and manage distributed air quality sensor networks at scale, including our proprietary air quality sensors (developed through years of R+D at MIT) and our integrated software platform.

We care deeply about using innovative technologies and socio-technological approaches to help businesses, governments, and community stakeholders obtain actionable air quality information.

If you're looking for an opportunity that allows you to highlight your skills and solve one of society's most pressing environmental challenges, we would love to hear from you.

We are looking for a full-time Senior Data Scientist to join Quant

AQ. We’re a small team with a rapidly expanding product-market fit, so as an individual contributor, you will quickly gain end-to-end ownership over multiple areas of the business. If that excites you, let’s talk!

The ideal candidate is an experienced atmospheric data scientist who is excited about the opportunity to apply their data science, machine learning, and atmospheric science skills to improve our category-leading air quality sensors. At Quant

AQ, we gather a lot of air quality data and need to improve our tooling and operations for synthesizing this incoming data to make it as useful as possible to act upon. Over the past decade, we have published some of the most highly-cited and widely-used ML methods for air quality sensors and sensor networks on topics ranging from models for improving individual sensor measurements (supervised regression models) to classifying types and sources of pollution (unsupervised classification methods).

You will help develop and improve novel approaches to measuring and locating sources of air pollution and help push those models from ideation to production for our global fleet of air quality sensors. If this sounds appealing, we would love to hear from you.

This position is based in Somerville, MA, at our HQ within Greentown Labs.

In this position, you will work directly with and report to the CEO, who is currently responsible for overseeing all data science efforts. Responsibilities of this position include:

• Develop internal and external tools and pipelines to help evaluate the continuous success of our fleet of sensors

• Develop improved algorithms for air sensors to improve performance and reliability

• Apply statistical methods to determine failure rates and lifetimes of key sensor components

• Manage our growing database of performance evaluation data and co-location datasets to help develop a better understanding of our sensor performance

• Partner closely with product and engineering to identify and prioritize the most important data science projects

• Develop and maintain customer-facing data science tools to help customers and the broader scientific community use air quality data and air quality sensors

• Stay up-to-date with the ML literature, especially with respect to its applications for air quality sensors and sensor networks

• Provide data-related customer support on an as-needed basis

• Develop and execute re-usable playbooks for common customer-facing data science needs (i.e., pilot project evaluation)

Candidates need not meet all requirements below, but the more that you meet, the better match you may be for existing work. Learning new tools on the fly is expected and hopefully part of the fun.

• A Ph.D. or M.S. in a quantitative field such as statistics, applied math, environmental science, computer science, operations research, or relevant work…