ML Platform Infra Engineer for Scalable AI Serving

Snap Inc.; Los Angeles (CA); On-site; USD 157,000 - 235,000; Full time

Benefits offered by this job

Paid parental leave

Comprehensive medical coverage

Mental health support programs

Equity in RSUs

Job summary

Snap Inc. is seeking a Software Engineer to join the ML Platform Experience team. You will design and optimize ML infrastructure at scale, build data pipelines for online inference and offline training, and develop high-performance model serving systems.

You will work with Python and Java, contributing to distributed systems and big data processing while collaborating across teams to deploy cutting-edge models into production and maintain rigorous security and quality standards.

Qualifications

• Bachelor's degree in computer science or equivalent.
• 2+ years post-Bachelors software development; or Masters 1 year; or PhD.
• Experience building large-scale production ML/inference systems.

Responsibilities

• Design and optimize infrastructure systems for ML workloads at scale.
• Build feature generation and serving pipelines for online/offline data.
• Develop high-performance inference systems for model serving.
• Create scalable ML training, evaluation, and inference in cloud.
• Develop data management for collection, labeling, processing, evaluation.
• Collaborate with ML engineers to deploy models to production.
• Use AI tools and fast workflows while ensuring code quality and security.
• Uphold production-ready standards across the stack.

Skills

Python

Java

Distributed systems

Big data

Spark

Flink

Ray

Team collaboration

Reliability/scale

Learning new concepts

Education

Bachelor's degree in CS or related

Master's or PhD appreciated

Job description

Snap Inc. is seeking a Software Engineer to join the ML Platform Experience team. You will design and optimize ML infrastructure at scale, build data pipelines for online inference and offline training, and develop high-performance model serving systems.

You will work with Python and Java, contributing to distributed systems and big data processing while collaborating across teams to deploy cutting-edge models into production and maintain rigorous security and quality standards.