ML Infra Engineer – Content Retrieval at Scale

Relha LLC; Palo Alto, Northern (CA, KY); Hybrid; USD 157,000 - 235,000; Full time

Benefits offered by this job

Paid parental leave

Comprehensive medical coverage

Emotional and mental health support

Equity / RSU

Job summary

Snap Inc. is seeking a Software Engineer for ML Infrastructure in California to design and operate large-scale retrieval and ML systems. You will work on feature generation, serving pipelines, and high-performance inference, collaborating with ML engineers to deploy models into production.

The role emphasizes scalable data workflows, distributed systems expertise, and leveraging Python and Java for performance-critical components. Office-based with a strong emphasis on privacy and security.

Qualifications

• Bachelor’s degree in a technical field or equivalent experience.
• 2+ years of post-Bachelor’s software development experience or 1+ year with a Master’s.
• Experience building large scale production ML systems and distributed systems.
• Familiarity with ML frameworks and data processing tools.

Responsibilities

• Design and optimize infrastructure for ML workloads at scale.
• Build feature generation and serving pipelines for online inferencing and offline data generation.
• Develop high-performance inference systems for model serving.
• Build scalable data collection, labeling, processing, and evaluation pipelines.
• Collaborate with ML engineers to deploy models into production.
• Ensure code correctness, security, and production-ready quality.

Skills

Python

Java

Distributed systems

Problem solving

Collaboration

Scaleable ML infrastructure

Model serving

Education

Bachelor's degree in Computer Science or related field

Masters/PhD in technical field (preferred)

Tools

TensorFlow

PyTorch

Caffe2

Spark

Flink

Ray

Job description

Snap Inc. is seeking a Software Engineer for ML Infrastructure in California to design and operate large-scale retrieval and ML systems. You will work on feature generation, serving pipelines, and high-performance inference, collaborating with ML engineers to deploy models into production.

The role emphasizes scalable data workflows, distributed systems expertise, and leveraging Python and Java for performance-critical components. Office-based with a strong emphasis on privacy and security.