AI Infrastructure Engineer
San Francisco • FullTime
Posted 2y ago
Remote Work Policy
On-site
Employment Type
FullTime
Categories
AI Infrastructure Engineer
About the job
Spellbrush, a leading generative AI studio, is seeking an AI Infrastructure Engineer to build and manage end-to-end ML infrastructure for running their state-of-the-art models across all platforms. This role involves designing and implementing next-generation inference architectures to support mobile and web applications, serving millions of users. The ideal candidate will work within a fast-paced, nimble team alongside top AI researchers, contributing to cutting-edge image generation models.
Responsibilities
- Design, implement, and operate next-generation inference architecture for all models across mobile, web, and other platforms.
- Collaborate with a fast-paced team developing state-of-the-art image generation models.
Requirements
- Experience with large distributed systems.
- Familiarity with technologies like K8S, Kafka, NATS, and Redis.
- Experience with both on-prem and multi-cloud clusters.
- Deep understanding of system tradeoffs and failure modes.
- Excellent understanding of handling large GPU workloads.
- Experience deploying or optimizing GPU workloads end-to-end is a plus.
- Comfortable working on small, fast-paced teams.
- Passion for anime aesthetic is a plus.
Benefits
- Equity
- Top-tier employer-sponsored health, dental, and vision insurance
- Additional perks