Senior MLOps Engineer (Generative Diffusion Models) at Eventum ai

Senior MLOps Engineer (Generative Diffusion Models)
Eventum ai
55 to 95 usd per hour
Remote (full‑time 1‑3 week sprint, then ongoing 20hr/week)

Consumer mobile app that lets users design apparel through a proprietary diffusion model.

Responsibilities:
• Productionise the text‑to‑image API — containerise, deploy, and autoscale the model on AWS/GCP/Kubernetes
• Cut latency from ≈30 s to ≤4 s while maintaining image quality
• Controlling GPU
• Implement monitoring
• Embed CI/CD & IaC (GitHub Actions, Terraform, Helm)
• Documentation

Requirements:
• 5+ years generative models at scale
• Strong Python
• Containerisation & orchestration (Docker, K8s); IaC (Terraform, Pulumi) and CI/CD pipelines
• Monitoring (Prometheus, Grafana, Loki, ELK)

Optional:
• Direct experience with diffusion or large‑image‑generation models (Stable Diffusion, DALL·E, Imagen, etc.)
• Cloud ops chops (AWS/GCP preferred) including autoscaling groups, load balancers, VPC networking, IAM security
• TensorRT

Contacts:
📧 jobs@eventum.ai