ML Routing Engineer: Real-Time, Scalable Rideshare ML

Lyft; Toronto; Hybrid; CAD 119,000 - 149,000; Full time

Benefits offered by this job

Extended health and dental coverage

Mental health benefits

Family building benefits

Child care and pet benefits

Lyft Health Care Savings Account

RRSP with company match

Flexible paid time off

Paid parental leave (18 weeks)

Subsidized commuter benefits

Lyft ride credits

Job summary

Lyft is hiring a Machine Learning Engineer to join the Routing team in Toronto. You will work on systems that provide routes for every ride request, processing millions of route queries daily with a focus on low latency, reliability, and accuracy.

The role involves developing ML and optimization models, writing production-grade code, and collaborating with software engineering, ML, and data science teams in a hybrid in-office setting.

Qualifications

• BS/MS/PhD in Computer Science or related quantitative field.
• 3+ years of Machine Learning experience.
• Nice-to-have: big data processing / distributed pipelines; Airflow and Spark/Flink.
• Proficiency in SQL (MySQL, PostgreSQL, SQL Server, Oracle).
• Ability to work in distributed teams across time zones (EST/PST).

Responsibilities

• Perform data analysis and build proofs-of-concept to compare ML and non-ML solutions.
• Balance model accuracy with productization complexity and runtime performance.
• Develop statistical, ML, or optimization models.
• Write production-quality code that scales to millions of requests per day.
• Participate in code reviews, design reviews, and on-call support.
• Write well-crafted, well-tested, readable, maintainable code.

Skills

Machine Learning

SQL

Distributed teamwork

Python

Education

CS degree or quantitative field

Tools

Apache Airflow

Spark

Flink

AWS

Kubernetes

Job description

Lyft is hiring a Machine Learning Engineer to join the Routing team in Toronto. You will work on systems that provide routes for every ride request, processing millions of route queries daily with a focus on low latency, reliability, and accuracy.

The role involves developing ML and optimization models, writing production-grade code, and collaborating with software engineering, ML, and data science teams in a hybrid in-office setting.