Software Engineer, ML infrastructure, Core Inference, Level 4

Snap Inc is a technology company. We believe the camera presents the greatest opportunity to improve the way people live and communicate. Snap contributes to human progress by empowering people to express themselves, live in the moment, learn about the world, and have fun together. The Company operates Snapchat , a visual messaging app that enhances your relationships with friends, family, and the world, and Specs Inc. , a wholly-owned subsidiary dedicated to making computing more human, in addition to Bitmoji , Saturn, and other digital services. Snap Engineering teams build fun and technically sophisticated products that reach hundreds of millions of Snapchatters around the world, every day. We’re deeply committed to the well-being of everyone in our global community, which is why our values are at the root of everything we do. We move fast, with precision, and always execute with privacy at the forefront. We’re looking for a Software Engineer to join the Core Inference team , part of the core ML Platform organization. Our team builds and owns the machine learning infrastructure that powers personalized experiences across Snap. As a centralized ML platform team, we enable teams across the company to deploy, optimize, and serve sophisticated machine learning models reliably and efficiently at scale. We own the end-to-end inference stack for recommendation models, embedding-generation models, and self-hosted large language models. Our platform supports nearly every major organization at Snap, including Ads, Content, Growth, Lenses, Security, and My AI. What you’ll do: Support the models powering personalized experiences across Discover, Stories, Spotlight, and other Snap products with ranking needs. Optimize, export, and prepare models for efficient production use while working across training and inference. Own the infrastructure used to host and serve recommendation models, embedding-generation models, and self-hosted LLMs. 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 the inference components that power advertising models, while Ads teams generally own the 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 those products require model hosting or serving. Knowledge, Skills & Abilities: Strong programming skills in Python, Java Strong problem-solving skills with a focus on system performance, scalability, and efficiency Good understanding of distributed systems and the infrastructure components of large-scale ML  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 to remain at the forefront of engineering trends and modern development practices Minimum Qualifications: Bachelor’s degree in a technical field such as computer science or equivalent experience 2+ years of post-Bachelor’s software development experience; or Master’s degree in a technical field + 1+ year of post-grad software development experience; or PhD in a relevant technical field Experience building large scale production machine learning systems, distributed systems or big data processing Preferred Qualifications: Masters/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 "Default Together"