ML Infrastructure Engineer - Scale & Deploy AI Models

SNAP, Inc.; Iowa (LA); Hybrid; USD 150,000 - 230,000; Full time

Benefits offered by this job

Parental leave & fertility benefits

Health, dental, vision insurance

401(k) with company match

Wellness programs

Job summary

Snap Inc. is seeking an experienced ML Infrastructure Engineer to design and optimize large-scale AI systems. You will develop high-performance inference and training infrastructure in the cloud, while building data pipelines for labeling and evaluation.

The role collaborates with ML engineers to deploy cutting-edge models in production, focusing on reliability, efficiency, and scalable data management across teams.

Qualifications

• Experience building and operating large-scale ML infrastructure.
• Strong programming skills in Python, Java, Scala or C++.
• Knowledge of distributed systems and data processing frameworks.

Responsibilities

• Design and optimize infrastructure for ML workloads at scale.
• Develop high-performance inference systems for fast model serving.
• Build scalable ML training, evaluation and inference in the cloud.
• Create data management systems for collection, labeling, processing and evaluation.
• Work on vector search algorithms to improve retrieval systems.

Skills

Python

Java

Scala

C++

Distributed systems

System performance

ML infrastructure

Big data processing

Troubleshooting

Learning on the job

Education

Bachelor’s degree in a technical field

Master’s degree in a technical field

PhD in a technical field

Tools

Spark

Flink

Ray

Job description

Snap Inc. is seeking an experienced ML Infrastructure Engineer to design and optimize large-scale AI systems. You will develop high-performance inference and training infrastructure in the cloud, while building data pipelines for labeling and evaluation.

The role collaborates with ML engineers to deploy cutting-edge models in production, focusing on reliability, efficiency, and scalable data management across teams.