Lead Data Scientist

3+ months agoSeattle, WA

Amperity is more than just a leading Customer Data Platform — it's a unique mix of people, technology, and opportunity. The people are whip-smart, deeply committed, and energizing. The technology is multi-patented, AI-powered, industry-shaping customer data management software that we invented because there was no way to solve the problems that we wanted to help consumer brands overcome. The opportunity is twofold: a market opportunity to provide a solution that consumer brands have been trying to find for decades, and a personal opportunity to grow and learn and hitch your career to a rocket ship. 

Since our founding in 2016, Amperity has been growing 2.5X year-over-year. We've raised $187M in funding, including a recent Series D that increased our valuation to over one billion dollars. We're going places, fast, and we want you to come with us. 

We help these brands make sense of massive amounts of transaction and engagement data so that they can finally know who their customers are, what opportunities exist, and how to provide the kinds of experiences that delight consumers and move the business metrics that matter. Our customers include Starbucks, Alaska Airlines, Patagonia, Kroger, J. Crew, Brooks Running, Planet Fitness, DICK's Sporting Goods, and many more. 

We're building something that's never existed before, and we're doing it in a way that's great for consumers, transformational for our customers, and career-making for the members of the Amperity team. Come help us make it happen!

The Team

The data science team at Amperity is a close-knit community of engineers and data scientists that move quickly and motivate each other to think independently, work autonomously, handle ambiguity, and solve hard problems. We identify, design and implement algorithms that lie at the heart of our products:

  1. Identity matching: deduplicating and clustering billions of records to their underlying identities daily. Our customers use our predictions to analyze their customer base and create a personalized experience for their customers at every touchpoint.
  2. Predictive modeling: With unified and enriched customer profiles (thanks to our identity matching pipeline), we build advanced customer-centric models to predict metrics/behaviors such as customer lifetime value, product recommendations, discount sensitivity, and event propensity. 

In addition to algorithmic development, we value sharing our findings with the broader data science community.  We publish our research in top-tier peer-reviewed publications, engage with fellow data scientists by speaking at internal and external conferences, and also hold several patents focused on our core IP (with many more to come).

We’re looking for a Lead Data Scientist to join our rapidly growing data science team. As a Lead, you’ll have the opportunity to drive our efforts in developing state-of-the-art predictive models and ML techniques in identity resolution, marketing analytics, and user behavioral forecasting. Day to day, you’ll focus on developing new IP, improving the efficacy of existing models, and researching new methods as we continue to increase the surface area of our predictive modeling suite.

What You’ll Do

  • Self-driven research and prototyping to extract insights from massive databases of customer interactions with brands across retail, hospitality, dining, and more
  • Lead a team that’s making deep investments in experimental design, statistical rigor, and model interpretability
  • Ensure our models can be reliably reproduced and integrated with a platform driving insights for dozens (and soon to be hundreds) of leading brands
  • Develop IP in the form of patents, research papers, and conference presentations
  • Be part of an active (and fun) group of machine learning practitioners and data scientists distributed across New York and Seattle

About You

  • Undergraduate degree in a quantitative discipline (e.g. statistics, mathematics) with 4+ years of experience building out predictive models using advanced statistical or ML techniques in a production environment
  • Advanced degree, authored papers in well-known journals, and registered patents all strongly preferred
  • You have production-level competence to perform advanced modeling: coding skills (such as Python, Java, or Scala), experience with analytics & visualization tools (Pandas, R, SPSS, SQL, Hadoop, Tableau), and experience with distributed computing (Spark, TensorFlow, PyTorch)
  • Prior research in an industry setting in one of the following areas: entity matching, probabilistic databases, or predictive marketing analytics
  • Significant expertise in a broad set of ML concepts ranging from random forests to generative probabilistic models, along with model prototyping, tuning, and evaluation
  • Ability to synthesize complex ideas for both technical and non-technical audiences.  Good communication skills in conducting code reviews, writing technical documentation, and giving internal and external presentations. 



We offer all the benefits you’d expect from a great place to work: 100% employee healthcare coverage, transportation subsidies, a comfortable work environment with plenty of snacks, and other employee experience perks like events and activities, both in-person and remote. We also offer self-managed PTO and the flexibility to do your best work in the way that works for you. We provide an inclusive environment where you’ll be challenged to find and unlock your full potential, surrounded by a team of world-class people driving for excellence. 

Amperity is an equal opportunity employer and values diversity at our company. We do not discriminate on the basis of race, religion, color, national origin, gender, sexual orientation, gender identity, age, marital status, veteran status, or disability status.

Job ID: 2577047