Senior ML Inference Systems Engineer (Hybrid, On-Prem GPU)

Uniting Holding; Dublin; Hybrid; EUR 80,000 - 120,000; Full time

Benefits offered by this job

25 days paid annual leave

Free inference tokens

Remote work flexibility

Job summary

Uniting Holding seeks a Senior ML Systems Engineer (Inference) in Dublin to lead model serving and performance optimization. This role involves deploying and tuning large language models while directly impacting performance and reliability.

Ideal candidates will have over five years of experience in ML infrastructure, knowledge of GPU architectures, and proficiency in Python. The position offers a flexible hybrid work environment with competitive remuneration.

Qualifications

• 5+ years of experience in ML infrastructure.
• Experience deploying and tuning large language models.
• Strong knowledge of GPU architecture.

Responsibilities

• Deploy and operate AI models using high-performance frameworks.
• Profile and optimize inference workloads for performance.
• Lead GPU procurement and hardware planning decisions.

Skills

ML infrastructure experience

Large language models deployment

GPU architecture knowledge

Inference optimization techniques

Proficiency in Python

Linux and container orchestration

Education

BSc/MSc in Computer Science or related discipline

Tools

vLLM

SGLang

TensorRT-LLM

Kubernetes

AWS

Job description

Uniting Holding seeks a Senior ML Systems Engineer (Inference) in Dublin to lead model serving and performance optimization. This role involves deploying and tuning large language models while directly impacting performance and reliability.

Ideal candidates will have over five years of experience in ML infrastructure, knowledge of GPU architectures, and proficiency in Python. The position offers a flexible hybrid work environment with competitive remuneration.