Software Engineer (Model Deployment)
Core
Building the deployment and serving platform that ships new models, LoRAs, and updates to tens of millions of users safely and continuously.
Role type
Senior IC machine-learning infrastructure engineer (model deployment)
Builds
Zero-downtime rollout systems for models and LoRAs across hundreds of GPUs; automated pipelines from trained model to production including packaging, versioning, canarying, and rollback.
Domain
AI entertainment / Large-scale GPU infrastructure
Deliverable
production ML models
Required skills
ML deployment, infrastructure engineering, containerization, Kubernetes, autoscaling GPU workloads, CI/CD, system design
Preferred skills
End-to-end ownership, rapid iteration, high-velocity delivery
Technologies
Kubernetes, GPU clusters
Responsibilities
Design and implement zero-downtime rollout systems for new models and LoRAs; Automate the path from trained model to production; Orchestrate hundreds of GPUs to serve millions of image generations per day.
Seniority
Senior, hands-on IC