Senior ML Inference Systems Engineer (Hybrid, GPU Fleet)

TensorX; Dublin; Hybrid; EUR 120,000 - 180,000; Full time

Benefits offered by this job

Hybrid work

25 days paid annual leave

Central Dublin office

Free inference tokens

Job summary

TensorX, a sovereign AI infrastructure platform headquartered in Dublin, is seeking a Senior ML Systems Engineer (Inference). You will own the model serving layer, deploy and optimize LLMs, and plan GPU capacity across on-prem and AWS.

Based in Dublin with hybrid work options, you will work on vLLM, SGLang and TensorRT-LLM, benchmarking models and driving hardware roadmaps. You will collaborate with platform and product teams to raise the bar on reliability and performance.

Qualifications

• 5+ years of professional experience in ML infrastructure, systems engineering or a closely related discipline.
• Hands-on experience deploying and tuning large language models with modern inference frameworks.
• Strong working knowledge of GPU architecture and NVIDIA hardware.
• Experience with inference optimisation techniques including quantisation and batching.
• Proficiency in Python and systems-level code.
• Solid experience with Linux, containers and GPU workloads orchestration.

Responsibilities

• Deploy and operate open-source LLMs in production using vLLM, SGLang and TensorRT-LLM.
• Profile and tune inference workloads for latency, throughput and GPU utilisation.
• Benchmark new open-weight models and inform productisation decisions.
• Lead GPU procurement and future hardware roadmap decisions.
• Build and maintain the model fleet infrastructure across on-prem and AWS.
• Instrument the serving stack with metrics and drive incident response.

Skills

ML infrastructure

GPGPU knowledge

Python

Linux

Container orchestration

Benchmarking

CUDA basics

Inference frameworks

Communication skills

Ambiguity tolerance

Education

BSc/MSc in CS or related

Tools

vLLM

SGLang

TensorRT-LLM

CUDA

Job description

TensorX, a sovereign AI infrastructure platform headquartered in Dublin, is seeking a Senior ML Systems Engineer (Inference). You will own the model serving layer, deploy and optimize LLMs, and plan GPU capacity across on-prem and AWS.

Based in Dublin with hybrid work options, you will work on vLLM, SGLang and TensorRT-LLM, benchmarking models and driving hardware roadmaps. You will collaborate with platform and product teams to raise the bar on reliability and performance.