1 month ago
Sydney, AustraliaSenior
Responsibilities
- Build and operate the deployment and serving platform for models, LoRAs, and updates reaching tens of millions of users.
- Develop zero-downtime rollout systems across hundreds of GPUs.
- Automate model packaging, versioning, canarying, rollback, and the transition from training to production.
- Orchestrate GPU infrastructure serving millions of image generations per day.
- Own work end-to-end from understanding users and proposing solutions through implementation and iteration.
Requirements
- 5+ years of experience building software at scale, focused on ML deployment, infrastructure, or platform engineering.
- Experience shipping models to production, including containerization, Kubernetes orchestration, autoscaling GPU workloads, and CI/CD.
- Ability to take ownership and execute across the full development lifecycle.
Benefits
- Top-of-market compensation with meaningful equity upside; the listed range is cash plus equity with superannuation on top.
- Visa sponsorship and relocation assistance for people moving to Sydney.
- In-person work in Sydney, Australia.
- Company card for food, coffee, tools, and other work-related needs.
- Daily team lunch and dinner at the office.
- Unlimited workspace budget.
- Compensation reviews every six months, with bonuses and raises based on impact.
- Paid three-day work trial with travel and accommodation covered if needed.
Tech Stack
Categories
