Senior ML Systems Engineer, Inference (Hybrid/Remote)

TensorX in Dublin is seeking a Senior ML Systems Engineer (Inference) to own the model serving layer, selecting and evaluating open-source models and deploying them on our on-prem GPU fleet, with some workloads in AWS.

You will optimize latency, throughput and cost, work with vLLM, SGLang and TensorRT-LLM, lead GPU procurement, and shape our infrastructure and reliability through observability and scalable operations.