ML Infrastructure Engineer — Core Inference & Serving

Snap Inc.; Los Angeles (CA); On-site; USD 157,000 - 235,000; Full time

Benefits offered by this job

RSUs

Parental leave

Medical coverage

Mental health support

Job summary

Snap Inc. is seeking a Software Engineer to join the Core Inference team within the ML Platform. You will help build and own the infrastructure powering personalized experiences across Snap’s products, deploying, optimizing, and serving sophisticated models at scale.

You’ll work on end‑to‑end inference for recommendation and embedding generation models, including self‑hosted LLMs, across Ads, Content, Growth, and other areas. Strong Python/Java and distributed systems skills are essential.

Qualifications

• Bachelor’s degree in a technical field or equivalent experience.
• 2+ years of post‑Bachelor’s software development experience; or Master’s degree +1 year; or PhD.
• Experience building large scale production machine learning systems and distributed systems.

Responsibilities

• Support models powering personalized experiences across Snap products with ranking needs.
• Optimize, export, and prepare models for production use across training and inference.
• Own infrastructure to host and serve recommendation models, embedding‑generation models, and self‑hosted LLMs.
• Work on LLM fine‑tuning, RL infrastructure, serving, and inference optimization.
• Provide model hosting and serving capabilities to multiple product areas.

Skills

Python

Java

Distributed systems

ML infrastructure

Big data processing

Collaboration

Education

Bachelor’s degree in Computer Science or equivalent

MS/PhD in a technical field

Tools

Spark

Flink

Ray

TensorFlow

PyTorch

Job description

Snap Inc. is seeking a Software Engineer to join the Core Inference team within the ML Platform. You will help build and own the infrastructure powering personalized experiences across Snap’s products, deploying, optimizing, and serving sophisticated models at scale.

You’ll work on end‑to‑end inference for recommendation and embedding generation models, including self‑hosted LLMs, across Ads, Content, Growth, and other areas. Strong Python/Java and distributed systems skills are essential.