Senior LLM Inference Optimization Engineer

Lever, Inc.; Ireland; On-site; EUR 120,000 - 180,000; Full time

Benefits offered by this job

Competitive pay

Career growth

Ownership over technical work

Collaborative environment

International teams

Job summary

Lever, Inc. is seeking a Senior Machine Learning Engineer specialized in LLM and Vision-Language Model inference optimization, based in Ireland.

The role focuses on optimizing latency, throughput, memory usage, and cost per token across model artifacts to production deployments. You will work across model internals, serving architectures, and benchmarking, collaborating with kernel, platform, and research teams to deliver measurable production improvements.

Qualifications

• Strong software engineering skills in Python and PyTorch.
• Hands-on experience deploying, operating, or optimizing LLM/VLM inference systems.
• Experience with modern inference stacks such as vLLM, Triton, or TensorRT-LLM.

Responsibilities

• Own optimization initiatives for specific model families and endpoints.
• Evaluate inference engines and recommend serving configurations.
• Diagnose and resolve production performance regressions.
• Deploy, benchmark, and extend inference engines; optimize latency and throughput.

Skills

Python

PyTorch

LLM Inference

Performance optimization

Benchmarking

CUDA knowledge

Systems deployment

Cross-team collaboration

Tools

vLLM

SGLang

TensorRT-LLM

Triton Inference Server

Ray Serve

KServe

NVIDIA Dynamo

Job description

Lever, Inc. is seeking a Senior Machine Learning Engineer specialized in LLM and Vision-Language Model inference optimization, based in Ireland.

The role focuses on optimizing latency, throughput, memory usage, and cost per token across model artifacts to production deployments. You will work across model internals, serving architectures, and benchmarking, collaborating with kernel, platform, and research teams to deliver measurable production improvements.