Senior AI Inference Engineer - Self-Hosted

Firmus Technologies; Sydney; On-site; AUD 180,000 - 240,000; Full time

Job summary

Firmus Technologies, a global leader in AI infrastructure, seeks a Senior AI Engineer (Inferencing) to build and optimize self-hosted inference services for internal products and customers. You will shape the engineering foundation for model serving in our AI Factory, covering onboarding, endpoint provisioning, performance benchmarking, security, and ongoing lifecycle management.

You'll work with frameworks like TensorRT, Triton, and vLLM, optimize latency and throughput, and contribute to

Qualifications

• 5+ years of software engineering experience, including AI inference / model serving.
• Experience building production model-serving platforms and APIs.
• Strong Python skills; working proficiency in C++ or Go.

Responsibilities

• Build and operate self-hosted AI inference services for internal apps and customers.
• Define onboarding workflows for models and endpoints.
• Provide scalable, secure, and observable inference endpoints.
• Develop reusable deployment templates and self-service workflows.

Skills

Software engineering

AI inference

Distributed systems

Python

C++/Go

Kubernetes

GPU performance

Benchmarking

Tools

TensorRT-LLM

TensorRT

SGLang

vLLM

Triton Inference Server

NVIDIA Dynamo

NVIDIA NIM

CUDA

cuDNN

NCCL

Job description

Firmus Technologies, a global leader in AI infrastructure, seeks a Senior AI Engineer (Inferencing) to build and optimize self-hosted inference services for internal products and customers. You will shape the engineering foundation for model serving in our AI Factory, covering onboarding, endpoint provisioning, performance benchmarking, security, and ongoing lifecycle management.

You'll work with frameworks like TensorRT, Triton, and vLLM, optimize latency and throughput, and contribute to