Senior AI Infra Engineer — Scale GPU Clusters & LLMs

Heidi Health Corp.; City of Melbourne; On-site; AUD 150,000 - 210,000; Full time

Benefits offered by this job

Learning budget

Health allowance

Home office budget

Parental leave

Fertility support

Work from anywhere

Equity

Job summary

black.ai is scaling Heidi, our AI healthcare platform, and seeks an engineer to build and operate the underlying infrastructure that powers production models. You will own model-serving, GPU management, and cost-aware deployment strategies to keep services fast and reliable.

You'll collaborate with researchers and platform engineers to deploy new models, tune performance, and ensure observability across the stack. A hands-on mindset and passion for scalable systems are essential.

Qualifications

• Hands-on AI infrastructure experience in production.
• 1+ year building/operating LLM deployment, inference, or training.
• Experience with GPU workloads and scaling.
• Ability to design, implement, and own production systems.

Responsibilities

• Build and operate model-serving infrastructure.
• Manage GPU clusters and workload scheduling.
• Improve inference latency, throughput, and memory efficiency.
• Support distributed training and model iteration.
• Make deployments observable with dashboards and alerts.
• Own production reliability and incident response.
• Optimize compute costs across models and workloads.
• Create reusable platform tooling for the model team.

Skills

Engineering foundation

Production deployment

GPU clusters

Performance debugging

Python programming

Incident ownership

Tools

Kubernetes

Slurm

Triton Inference Server

TensorRT-LLM

vLLM

SGLang

Job description

black.ai is scaling Heidi, our AI healthcare platform, and seeks an engineer to build and operate the underlying infrastructure that powers production models. You will own model-serving, GPU management, and cost-aware deployment strategies to keep services fast and reliable.

You'll collaborate with researchers and platform engineers to deploy new models, tune performance, and ensure observability across the stack. A hands-on mindset and passion for scalable systems are essential.