Spellbrush
AI Infrastructure Engineer
San Francisco · Full-time · Posted Feb 7, 2024
- Visa sponsorship
- Visa sponsorships are available.
About the job
Build and operate end-to-end ML infrastructure and inference architecture for generative image models across platforms and applications.
What you'll do
- Design, implement, and run inference architecture for models powering mobile, web, and other platforms.
- Work with a team developing image-generation models serving over 16 million users.
What they ask for
- Experience with large distributed systems.
- Familiarity with K8S, Kafka, NATS, Redis, or similar systems.
- Deep understanding of distributed-system tradeoffs and failure modes.
Nice to have
- Experience deploying or optimizing GPU workloads end-to-end.
- Interest in anime aesthetics.
Tools
K8S, Kafka, NATS, Redis
AI focus
Develop and operate infrastructure for generative image models, including inference architecture and GPU workload deployment or optimization.
Model-written summary · the original posting is authoritative