ML Software Engineer, Integrity
Company: Lyft
Location: New York, NY
Salary: $140.8k - $176k per year
Type: Full-time
Level: mid
Posted: 2026-02-26
About this role
At Lyft, our purpose is to serve and connect. We aim to achieve this by cultivating a work environment where all team members belong and have the opportunity to thrive.
Our engineering team is growing rapidly, and we are looking for a Machine Learning Engineer. As a machine learning engineer, you will be developing and launching the algorithms that power the platform’s core services. Compared to similarly-sized technology companies, the set of problems that we tackle is incredibly diverse. They cut across transportation, economics, forecasting, mapping, personalization, and adaptive control. We are hiring motivated experts in each of these fields. We’re looking for someone who is passionate about solving problems with data, building reliable ML systems, and is excited about working in a fast-paced, innovative, and collegial environment.
An ML SWE in the Integrity team is a specialized role focusing on the application of machine learning to enhance fraud detection and prevention. This role operates at a leadership and system ownership level comparable to a general SWE but with a deep specialization in ML. The individual will contribute significantly to the team's engineering excellence and operational responsibilities.
This role is a highly specialized engineering position that leverages deep machine learning expertise to directly impact the Integrity team's core mission: reducing fraud, ensuring trust and safety on the Lyft platform, and contributing to the development of cutting-edge AI-driven fraud-fighting platforms.
Responsibilities:
- Core Responsibilities:
- Develop & Lead ML Project Initiatives for Integrity, Identity and Pay: Partner with Engineers, Data Scientists, Product Managers, and Business Partners across the organization to apply machine learning for business and user impact, specifically in areas such as (supervised) fraud risk scoring, (unsupervised) anomaly detection and other applications. Drive the end-to-end ...