Senior Machine Learning Engineer

Before 1965, it was extremely difficult and time-consuming to analyze complicated signals, like radio or images. You could solve it, but you had to throw a ton of compute at it. That all changed with the invention of the Fast Fourier transform, which could efficiently break that signal down into the frequencies that are a part of it. The Risk Onboarding team is working on efficiently reviewing customers’ applications without compromising on quality. We are the front line of defense for preventing money laundering and financial crimes, building systems to verify that someone is who they say they are and that we are allowed to do business with them. At Mercury, we are committed to crafting an exceptional banking* experience for startups. Our team is passionately focused on ensuring our products create a safe environment that meets the needs of our customers, administrators, and regulators. *Mercury is a fintech company, not an FDIC-insured bank. Banking services provided through Choice Financial Group and Column N.A., Members FDIC. As part of this role, you will: Partner with data science & engineering teams to design and deploy ML & Gen AI microservices, primarily focusing on automating reviews Work with a full-stack engineering team to embed these services into the overall review experience, including human in the loop, escalations, and feeding human decisions back into th [... source excerpt omitted ...] observability, alerting, and disaster recovery for all services Implement tracing, performance, and regression testing Feel a strong sense of product ownership and actively seek responsibility – we often self-organize on small/medium projects, and we want someone who’s excited to help shape and build Mercury’s future The ideal candidate for the role has: 7+ years of experience in roles like machine learning engineering, data engineering, backend software engineering, and/or devops Expertise with: A full modern data stack: Snowflake, dbt, Fivetran, Airbyte, Dagster, Airflow SQL, dbt, Python OLAP / OLTP data modelling and architecture Key-value stores: Redis, dynamoDB, or equiv [... source excerpt omitted ...] ovey as part of our hiring and / or promotional process for jobs in NYC and certain features may qualify it as an AEDT. As part of the evaluation process we provide Covey with job requirements and candidate submitted applications. We began using Covey Scout for Inbound on January 22, 2024. Please see the independent bias audit report covering our use of Covey here. #LI-RA1