# AI Infrastructure Engineer

**Company:** [Spellbrush](https://hotfix.jobs/companies/spellbrush)
**Location:** San Francisco, CA
**Role:** DevOps / SRE
**Skills:** Kubernetes, Kafka, Nats, Redis, GPU, Distributed Systems, Multi-Cloud, Inference Architecture
**Posted:** 2024-02-07

> Builds and runs end-to-end ML inference infrastructure for generative AI image models across mobile and web platforms. Requires expertise in distributed systems, Kubernetes, Kafka, Redis, GPUs, and multi-cloud environments.

## Job Description

## Responsibilities
- Design, implement and run next-generation inference architecture for running models powering all platforms and applications (mobile, web, etc.).
- Work alongside fast-paced team developing state-of-the-art image generation models serving over 16 million users.

## Requirements
- Experience with large distributed systems.
- Familiarity with K8S, Kafka, NATS, Redis, etc.
- Experience with on-prem and multi-cloud clusters.
- Deep understanding of tradeoffs and failure modes of systems.
- Excellent understanding of GPUs handling large workloads.
- Experience deploying or optimizing GPU workloads end-to-end is a huge plus.
- Comfortable working on small, fast-paced teams.

## Nice-to-Haves
- Passion for anime aesthetic.

## Similar roles

- [Software Engineer, Platform & Infrastructure](https://hotfix.jobs/jobs/2a4d6818-4e00-4a08-8339-aba841ed1ada) - Forus - New York, NY
- [Software Engineer, Developer Productivity](https://hotfix.jobs/jobs/3d3eb78d-cb73-4b62-bef0-6c84085fdf5a) - Forus - New York, NY
- [Site Reliability Engineer](https://hotfix.jobs/jobs/8def48bc-b809-4397-bd55-28b9747c1f82) - Runloop - San Francisco, CA
- [Build & Release Engineer](https://hotfix.jobs/jobs/c41c87c5-6007-46e9-8648-635789c39b4a) - Applied Intuition - Sunnyvale, CA - $118k – $200k/yr
- [Software Engineer, Async Platform](https://hotfix.jobs/jobs/f1db6fa3-5b80-4939-86b0-39e6f0db0694) - Lyft - Seattle, WA - $118k – $147k/yr

**Apply:** https://hotfix.jobs/jobs/d9e5ee0b-b068-457d-8f74-8fb43ddb8004
**Canonical:** https://hotfix.jobs/jobs/d9e5ee0b-b068-457d-8f74-8fb43ddb8004