AI Engineer, Inference at Firmus Technologies

Department: AI & Applications

Location: Sydney, New South Wales
Type: Full-time
Level: senior
Posted: Sep 7, 2026

Description

Firmus Technologies is hiring a Senior AI Engineer (Inferencing) to build and operate self-hosted AI inference services for internal products, customer-facing applications, and future Inference-as-a-service offerings. The role owns model onboarding, endpoint provisioning, runtime selection, performance optimization, observability, capacity management, security, and operational lifecycle management, and contributes benchmarked inference recipes and workload profiles to the Model-to-Grid product and agentic applications. The position requires 5+ years of software engineering experience, including 3+ years in AI inference or comparable performance-critical environments, and is available in Singapore or Australia (Launceston, Hobart, Sydney, Melbourne).

Required Skills

TensorRT-LLM
vLLM
CUDA
Kubernetes
Python
C++
Go
Quantization
Distributed inference
Observability
Performance profiling

Additional Information

Required Previous Experiences: 5+ years of software engineering experience, including 3+ years in AI inference, model serving, ML systems, high-performance computing, distributed systems, or comparable performance-critical environments.
Experience building, operating, or materially improving production model-serving platforms, inference APIs, GPU-backed services, AI developer platforms, or multi-tenant AI systems.
Hands-on experience with modern inference frameworks such as TensorRT-LLM, TensorRT, SGLang, vLLM, Triton Inference Server, NVIDIA Dynamo, NVIDIA NIM, or Hugging Face Text Generation Inference.
Experience with distributed inference or training patterns, including parallelism, collective communication, fault handling, and multi-node scaling.
Experience with inference benchmarking, performance profiling, reproducibility, load testing, regression testing, and analysis of throughput, latency, utilization, scaling, power, and cost metrics.
Translation Company Name: Firmus Technologies