Platform, Machine Learning Engineer
Affirm is reinventing credit to make it more honest and friendly, giving consumers the flexibility to buy now and pay later without any hidden fees or compounding interest.
Machine learning is a critical tool in this effort! As a member of the software engineering team, you will design, build, optimize, and support machine learning systems both offline and real time. You will also have the opportunity to partner with Data Science and product teams across Affirm, leveraging your machine learning and software development skills to solve challenging problems that will improve the financial lives of millions of people.
What you'll do
- Partner with Data Science and Product engineering teams to build production machine learning models; your models will decide who we lend to in real time, and how we interact with our existing customers
- Develop the core decisioning service supporting our machine learning models in production
- Optimize the decisioning service with respect to the accuracy of the underlying models, the latency of different 3rd party data sources, and the expected financial cost of those data sources
- Develop our understanding of new data sources and how they may improve our existing processes
- Design, develop, and deploy infrastructure for the training, testing, and serving of models at scale
- Work closely with Affirm’s credit, risk, and analytics teams to understand our risk modeling strategy and the business drivers underlying that strategy
What we look for
- B.S. with 2-3 years of industry experience, M.S. with 1-2 years, or PhD
- Deep understanding and experience with data engineering, data analysis, and statistical modeling, in the development of real-time services
- Proficiency writing production-quality software following software engineering best practices, preferably industry engineering experience with machine learning projects (e.g. recommendation, ranking, optimization)
- Strong foundation in machine learning with experience implementing and optimizing machine learning models
- Hands on experience with Python, Spark, XGBoost, Airflow, and AWS (EC2, EMR, etc.) a plus
- Ability to work efficiently both solo and as part of a team; willingness to learn new things
- Passion and drive to change consumer banking for the better, while developing a deeper understanding of applied machine learning
Location
“We’re excited to announce that Affirm is now a remote-first company! This role can be located anywhere in the U.S. Remote based employees may occasionally travel to an Affirm office for meetings or team building events. Our offices in San Francisco, New York City, Pittsburgh, Chicago, and Salt Lake City will remain operational and accessible for anyone to use on a voluntary basis.”
#LI-Remote
Check out our remote-first approach to learn more about the new ways we work.
If you got this far, we hope you're feeling excited about this role. Even if you don't feel you meet every single requirement, we still encourage you to apply. We're eager to meet people who believe in Affirm's mission and can contribute to our team in a variety of ways—not just candidates who check all the boxes.
At Affirm, People Come First is one of our core values, and that’s why diversity and inclusion are vital to our priorities as an equal opportunity employer. You can read about our D&I program here and our progress thus far in our 2020 DEI Report.
We also believe It’s On Us to provide an inclusive interview experience for all, including people with disabilities. We are happy to provide reasonable accommodations to candidates in need of individualized support during the hiring process.
We will consider for employment qualified applicants with arrest and conviction records in accordance with applicable federal, state, and local laws, including the San Francisco Fair Chance Ordinance. By clicking "Submit Application," I acknowledge that I have read the Affirm Employment Privacy Policy, and hereby consent to the collection, processing, use, and storage of my personal information as described therein.