Software Engineer (Model Deployment)

About the role

We are building a new category of interactive entertainment powered by AI characters, image, video, and real‑time experiences. As a Software Engineer (Model Deployment) you will own how our models reach production, building the deployment and serving platform that ships new models, LoRAs, and updates to tens of millions of users safely and continuously.

Key responsibilities

• Own the deployment and serving platform for models, LoRAs, and updates to millions of users.
• Build a zero‑downtime rollout system for new models and LoRAs across hundreds of GPUs.
• Automate the path from a trained model to production, including packaging, versioning, canarying, and rollback.
• Orchestrate hundreds of GPUs to serve millions of image generations per day.

Required profile

• 5+ years of experience building software at scale, focusing on ML deployment, infrastructure, or platform engineering.
• Experience shipping models to production: containerization, orchestration (Kubernetes), autoscaling GPU workloads, and CI/CD.
• Ability to get things done end‑to‑end from understanding users to implementation and iteration.
• Strong hunger to win and tackle challenging problems.

Required skills

• Kubernetes
• Docker (containerization)
• CI/CD pipelines
• GPU autoscaling

What we offer

• Top‑of‑market compensation with meaningful equity upside.
• Real ownership from day one with impact on important problems.
• Fast‑growing scope; responsibility and compensation grow with impact.
• Company card for food, coffee, tools, and anything that helps you do your best work.
• Daily team lunch and dinner at the office.
• Unlimited workspace budget to build your ideal setup.
• Visa sponsorship and relocation assistance for people moving to Sydney.