Software Engineer, ML infrastructure, Core Inference, Level 4
Overview:
As a Software Engineer on the Core Inference team, you help build and scale the ML infrastructure powering personalized experiences across Snap. You will own and optimize the end-to-end inference stack for recommendation models, embeddings, and self-hosted LLMs, enabling cross-functional teams to deploy and serve models efficiently. You'll work across training and inference to prepare models for production and improve system performance. This role offers the chance to shape how Snap delivers scalable, private ML-powered experiences to hundreds of millions of users. Compensation / Benefitspaid parental leavecomprehensive medical coverageemotional and mental health support programsequity in RSUscompetitive compensation packageswork-life balance options
Responsibilities:
- Own and operate the infrastructure for hosting and serving recommendation models, embeddings, and self-hosted LLMsOptimize, export, and prepare models for production use across training and inference
- Provide model-hosting and serving capabilities to multiple product teams (Ads, Content, Growth, Lenses, Security, My AI)
- Contribute to LLM fine-tuning, reinforcement learning infrastructure, serving, and inference optimization
- Deliver ranking and ML infrastructure support for products requiring model hosting or serving
Key requirements:
- 2+ years of software development experience (or advanced degree)
- Strong programming skills in Python and Java
- Experience with distributed systems and large-scale ML infrastructure
- Experience with big data processing frameworks (Spark, Flink, or Ray)
- Proven track record of operating highly-available systems at scale
- Ability to learn new concepts quickly and adapt to evolving AI toolscollaboration and teamworkproactive learningproblem-solving with focus on performance and scalability
- PythonJavadistributed systems