Senior AI Infrastructure Engineer

At Heidi AI, the engineering team focuses on developing and maintaining the infrastructure that supports AI models used in healthcare applications. The team is responsible for ensuring that models are deployed efficiently, reliably, and at scale, supporting millions of patient sessions worldwide. The role involves working closely with researchers and platform engineers to optimize GPU clusters, model serving, and deployment pipelines, all within a hybrid work environment in Melbourne.

The senior AI infrastructure engineer will design, build, and operate systems for model deployment, inference, and training. Key tasks include managing GPU workloads, improving inference latency, supporting distributed training, and ensuring system observability and reliability. The role demands hands-on experience with large language models, GPU orchestration, and performance debugging, with a focus on cost-effective, scalable solutions.

Candidates should have at least one year of experience in AI infrastructure, including deploying large ML models, managing GPU clusters, and working with deployment tools like Triton or TensorRT. Proficiency in Python and systems programming languages, Linux, containers, and automation is essential. The position is full-time, hybrid, and based in Melbourne, with a focus on building a platform that empowers the model team to operate independently.