Senior GPU ML Inference Engineer End-to-End High-Throughput

coreflow is redefining entertainment with AI and operates in Sydney, Australia. We seek an experienced engineer to own our model inference stack end-to-end, delivering low-latency in-house and open-source models to millions of users.

Ideal candidates have 5+ years building software at scale, deep GPU inference knowledge (batching, quantization, vLLM/TensorRT/Triton) and a proven ability to ship impactful systems from concept to production. Visa sponsorship available, based in Sydney.