Software Engineer, ML Infrastructure, Core Inference, Level 4

Snap Inc. • Palo Alto, CA

6d • $133,000 - $235,000 • Onsite

About The Position

Snap Inc. is seeking a Software Engineer to join the Core Inference team within its core ML Platform organization. The team builds and owns machine learning infrastructure that enables teams across Snap to deploy, optimize, and serve sophisticated models reliably and efficiently at scale. It owns the end-to-end inference stack for recommendation models, embedding-generation models, and self-hosted large language models, supporting organizations including Ads, Content, Growth, Lenses, Security, and My AI.

The engineer will support models powering personalized experiences across Snap products, prepare and optimize models for production, and build infrastructure for model hosting and serving. The role also covers LLM fine-tuning, reinforcement learning infrastructure, serving, and inference optimization, as well as ranking and ML infrastructure for products that require model hosting or serving. Snap follows a default-together approach, with team members expected to work in an office at least four days per week.

Requirements

• Strong programming skills in Python and Java.
• Strong problem-solving skills focused on system performance, scalability, and efficiency.
• Good understanding of distributed systems and infrastructure components for large-scale machine learning.
• Experience with big data processing frameworks such as Spark, Flink, or Ray.
• Ability to collaborate and work well with others.
• Proven track record of operating highly available systems at significant scale.
• Ability to proactively learn new concepts and apply them at work.
• Adaptability in learning and applying evolving AI systems and tools and modern development practices.
• Bachelor’s degree in a technical field such as computer science, or equivalent experience.
• At least 2 years of post-Bachelor’s software development experience; or a technical Master’s degree and at least 1 year of post-graduate software development experience; or a PhD in a relevant technical field.
• Experience building large-scale production machine learning systems, distributed systems, or big data processing.

Nice To Haves

• Master’s or PhD in a technical field such as computer science, or equivalent industry experience.
• Experience working with ML training platforms or optimizing AI model inference.
• Familiarity with ML frameworks such as TensorFlow, PyTorch, Caffe2, Spark ML, scikit-learn, or related frameworks.

Responsibilities

• Support models powering personalized experiences across Discover, Stories, Spotlight, and other Snap products with ranking needs.
• Optimize, export, and prepare models for efficient production use, working across training and inference.
• Own infrastructure for hosting and serving recommendation models, embedding-generation models, and self-hosted large language models.
• Work on LLM fine-tuning, reinforcement learning infrastructure, serving, and inference optimization.
• Provide model-hosting and serving capabilities to teams across Ads, Content, Growth, Lenses, Security, My AI, and other product areas.
• Own inference components that power advertising models; Ads teams generally own ad products, formats, modeling objectives, and ranking strategies.
• Provide ranking and ML infrastructure for products such as Camera, Creative Tools, Maps, Chat, Memories, Games, and Minis when they require model hosting or serving.

Benefits

• Paid parental leave.
• Comprehensive medical coverage.
• Emotional and mental health support programs.
• Compensation packages that allow employees to share in Snap’s long-term success.
• Equity in the form of RSUs.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level