We are looking for a killer infrastructure/backend engineer who can help with the core product infra and model training infra.

We have a major gap to fill with someone who is fast-paced, detail-oriented, and hungry to grow.

The experience we are looking for: 1. Experience building and scaling GPU-based inference services, optimizing for both low latency and high resource utilization.

2. Experience with job orchestration and load balancing with parallel generations, heterogeneous resource constraints (GPU, CPU, I/O), and multi-tiered queues.

3. Experience implementing observability for latency attribution and failure diagnosis for multi-stage, asynchronous, and cross-platform pipelines.

4. Experience designing fan-out architectures where upstream job completion triggers multiple independent downstream consumers that have mixed criticality.

5. Familiarity with modern cloud infrastructure: managed databases, job queues, edge compute/CDN, and PaaS deployment platforms.

6. Experience coding with a variety of backends (servers in Python, Typescript, Rust).

7. Experience deploying to different infrastructures (AWS, Cloudflare, Railway, etc).

If this fits you, email me at nick@drafted.ai to schedule an intro call.