Senior LLM Inference & GPU Performance Engineer

Confidential; Ireland; On-site; EUR 70,000 - 90,000; Full time

Job summary

Confidential company in Ireland is seeking a specialist to optimize the performance of large language models in production, focusing on latency, throughput, and cost. The role involves working deeply at the GPU level and applying various optimization strategies to improve efficiency.

Candidates must have extensive experience in optimizing deep-learning models and hands-on GPU programming skills. If you have a knack for measurable performance improvements and want to work in a high-impact area, this could be for you!

Qualifications

• Deep experience optimizing deep-learning inference in production.
• Hands-on GPU programming and performance engineering (CUDA or equivalent).
• Fluency with modern LLM serving stacks.
• Track record of measurable performance wins.

Responsibilities

• Optimize LLM inference for latency, throughput, and cost.
• Profile and tune GPU performance.
• Get the most out of serving frameworks.
• Partner with model and platform teams.

Skills

Optimizing deep-learning inference

GPU programming (CUDA)

Performance engineering

LLM serving stacks (vLLM, TensorRT-LLM)

Job description

Confidential company in Ireland is seeking a specialist to optimize the performance of large language models in production, focusing on latency, throughput, and cost. The role involves working deeply at the GPU level and applying various optimization strategies to improve efficiency.

Candidates must have extensive experience in optimizing deep-learning models and hands-on GPU programming skills. If you have a knack for measurable performance improvements and want to work in a high-impact area, this could be for you!