ML Infra Engineer - Scalable Training & Inference (Equity)

Snapchat; Palo Alto (CA); On-site; USD 209,000 - 313,000; Full time

Job summary

Snap Inc. in Palo Alto, CA is seeking a Software Engineer for the ML Platform team to scale ML infrastructure, optimize AI training and inference, and support production model deployment.

You will design high-performance inference pipelines, work with data platforms, and collaborate with ML engineers to bring cutting-edge models into production. The role emphasizes reliability, efficiency, and office presence 4+ days per week.

Qualifications

• Bachelor’s degree in computer science or equivalent.
• 6+ years of post-Bachelor’s software development experience.
• Experience building large-scale production ML systems.

Responsibilities

• Design and optimize infrastructure systems for ML workloads at scale.
• Develop high-performance inference systems for fast model serving.
• Collaborate with ML engineers to deploy models into production.

Skills

Python

Java

Scala

C++

Distributed systems

Problem solving

Education

Bachelor’s degree in computer science or equivalent

Tools

Spark

Flink

Ray

Job description

Snap Inc. in Palo Alto, CA is seeking a Software Engineer for the ML Platform team to scale ML infrastructure, optimize AI training and inference, and support production model deployment.

You will design high-performance inference pipelines, work with data platforms, and collaborate with ML engineers to bring cutting-edge models into production. The role emphasizes reliability, efficiency, and office presence 4+ days per week.