Latest AI JobsBrowse Jobs
heidihealth.com.au logo

Senior AI Infrastructure Engineer

heidihealth.com.auMelbourneEngineering
Apply on company site
Salary
Not listed
Job type
Full-time
Work mode
Remote
Experience
Senior · 1+ yrs
Posted
14 Sept 2026
Status
Open · checked 7d ago

About this role

Located in Melbourne, the Senior AI Infrastructure Engineer role at heidihealth.com.au involves building and operating scalable systems for clinical AI models. This position suits a hands-on engineer with production experience in machine learning infrastructure who wants to support global healthcare technology.

Role Overview

This position sits in the model team at heidihealth.com.au, focusing on the infrastructure that trains, deploys, and scales AI models for medical products. The engineer manages GPU clusters, optimizes inference performance, and builds reliable deployment pipelines to support clinical workflows across multiple regions.

Key Responsibilities

Build and own model-serving infrastructure, implementing deployment pipelines, autoscaling, fallback paths, and region rollouts.
Manage GPU clusters and workload scheduling to balance inference, training, and evaluation capacity.
Improve inference performance by analyzing latency, throughput, memory efficiency, and batching strategies.
Support distributed training and model iteration by providing reliable job launching, artifact management, and checkpoint handling.
Make deployments observable by connecting application requests to worker configurations and building monitoring dashboards.
Own production reliability by defining service objectives, investigating incidents, and creating recovery runbooks.
Track compute costs, GPU usage, and idle capacity to improve cost per successful request.
Build independent platforms and automate provisioning and benchmarking for research and engineering teams.

Requirements

Strong engineering foundation with at least 1 year of hands-on AI infrastructure experience building and operating large language model systems.
Production model deployment experience using engines like vLLM, SGLang, TensorRT-LLM, or Triton Inference Server.
GPU cluster and orchestration experience using Kubernetes, Slurm, or equivalent platforms.
Performance debugging skills using traces, metrics, and profiling tools to identify bottlenecks.
Proficiency in Python and backend or systems development experience in Go, C++, or Rust.
Operational ownership experience managing production incidents, monitoring, and release recovery.

Nice to Have

Experience with distributed training frameworks such as PyTorch FSDP or Megatron, or reinforcement learning infrastructure.
Background tuning inference engines, serving Mixture of Experts models, or implementing quantization and speculative decoding.
Familiarity with GPU interconnects, NCCL, RDMA, topology-aware scheduling, or multi-node troubleshooting.
CUDA or Triton kernel development experience, or contributions to open-source AI infrastructure projects.
Experience operating infrastructure across multiple regions or providers for sensitive workloads.

Skills and Tools

Python
Go
C++
Rust
Kubernetes
Slurm
vLLM
SGLang
TensorRT-LLM
Triton Inference Server
PyTorch FSDP
Megatron
CUDA
Triton
NCCL
RDMA

About the Company

Heidi builds clinical AI products designed to absorb administrative tasks and support patient sessions globally. The organization focuses on real-world impact in healthcare systems, aiming to double global healthcare capacity and strengthen human connections in medicine.

How to Apply

Applicants should apply directly on the official company careers page.

Skills and tech stack

PythonGoC++RustKubernetesSlurmvLLMSGLangTensorRT-LLMTriton Inference ServerPyTorch FSDPMegatronCUDATritonNCCLRDMAPyTorchLLMLLMsReinforcement LearningFine-tuning

Questions candidates ask

What is the location of the Senior AI Infrastructure Engineer role?

The role is located in Melbourne.

What team does this position belong to?

This position sits in the model team, working alongside researchers and engineers who train, deploy, and own AI models.

How many years of experience are required?

The role requires at least 1 year of hands-on AI infrastructure experience building and operating infrastructure for large language models.

What programming languages are required?

Engineers must be proficient in Python and comfortable with backend or systems development in Go, C++, Rust, or a comparable language.

What inference engines are mentioned in the requirements?

Relevant inference engines include vLLM, SGLang, TensorRT-LLM, and Triton Inference Server.

Ready to apply?

The application is on the official heidihealth.com.au careers page.

Apply on company site