about 3 hours ago
Sydney, Australia or Melbourne, AustraliaMid Level / Senior
H1B Sponsor
Responsibilities
- Design, deploy, and maintain AWS/EKS infrastructure for GPU-backed model workloads.
- Manage GPU node pools and tune autoscaling for inference traffic patterns.
- Write and maintain infrastructure as code in Terraform.
- Build tooling to measure model performance, including clinical accuracy and latency.
- Design offline evaluation harnesses and automated regression tests.
- Own GPU utilization and model routing strategies.
- Collaborate with product engineers and clinicians on model data pipelines.
- Instrument observability metrics and define alerting thresholds.
Requirements
- Strong experience with AWS and Kubernetes, particularly EKS and GPU workload scheduling.
- Practical LLMOps experience with model serving frameworks and deployment strategies.
- Proficiency in Python and understanding of ML concepts related to model fine-tuning.
- Fluency in infrastructure-as-code using Terraform.
- Experience building evaluation frameworks for generative models.
- Strong engineering habits with a focus on code quality and tech debt management.
- Willingness to engage with the clinical domain and understand the implications of model failures.
Benefits
- Flexible hybrid working environment with 3 days in the office.
- Generous personal development budget of $500 per annum.
- Opportunity to learn from experienced engineers and creatives in a diverse team.
- Equity ownership in the company.
- Chance to create a global impact in a leading healthtech startup.
- Opportunity to fast track your startup career based on impact.