GPU Model Engineer for Loes — Run & Benchmark (Remote NL)

HostYourAI

Nederland

Hybrid

EUR 70,000 - 100,000

Full time

14 days+

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

HostYourAI is seeking an experienced ML engineer to run open models on GPUs across Europe, focusing on speed, reliability, and cost per token. You will help deploy vLLM and SGLang, optimize VRAM usage and quantization, and build robust eval harnesses to ensure consistent model quality.

The role involves training and finetuning language models, creating datasets, and evaluating new versions against the baseline.

Qualifications

  • Experience running models on GPUs (vLLM, SGLang or similar) and training/finetuning language models (SFT, DPO, LoRA) or both.
  • You measure performance with benchmarks, evals, and statistics where needed.
  • Proficiency with Python, Linux and containers, and the common ML tooling (Hugging Face, PyTorch). Learning fast is valued.
  • Fluent English; Dutch is a genuine plus and you should be based in the Netherlands.
  • Independent, self-directed work style with minimal supervision.

Responsibilities

  • Get models running and keep them running on GPUs, optimizing fit and price from VRAM estimates to quantization.
  • Measure throughput, latency, and cost per token to keep economics sharp.
  • Build an eval harness to ensure all hosted models meet a consistent standard (quality, grounding, tool calling, speed).
  • Improve Loes by building datasets, running finetunes and validating versions against previous ones.
  • Publish model cards and benchmarks with transparency information per model.

Skills

GPU deployment
Python
Linux
Containers
Hugging Face
PyTorch
Benchmarks
English fluency

Tools

vLLM
SGLang
Docker
Hugging Face
PyTorch

Job description

HostYourAI is seeking an experienced ML engineer to run open models on GPUs across Europe, focusing on speed, reliability, and cost per token. You will help deploy vLLM and SGLang, optimize VRAM usage and quantization, and build robust eval harnesses to ensure consistent model quality.

The role involves training and finetuning language models, creating datasets, and evaluating new versions against the baseline.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Context Engineer Loes
Context Engineer Loes

HostYourAI • Nederland

Hybrid
EUR 70,000 - 100,000
Lead GPU ML Infrastructure & Acceleration Engineer
Lead GPU ML Infrastructure & Acceleration Engineer

Prosus • Amsterdam

Hybrid
EUR 120,000 - 180,000
Hybrid work model
Amsterdam office
Remote LLM Evaluation Engineer - AI Research & Benchmarks
Remote LLM Evaluation Engineer - AI Research & Benchmarks

Blue Lynx Employment BV • Netherlands

Remote
EUR 60,000 - 80,000
25 holidays per annum
Pension plan
Opportunity to work on cutting-edge AI initiatives
GPU ML Infrastructure Engineer — End-to-End Acceleration
GPU ML Infrastructure Engineer — End-to-End Acceleration

Arbeitnow • Amsterdam

Hybrid
EUR 110,000 - 140,000
Hybrid work model
Competitive compensation
MacBook Pro
+1
Senior LLM Engineer - Distributed Training & RLHF
Senior LLM Engineer - Distributed Training & RLHF

Prosus • Amsterdam

Hybrid
EUR 120,000 - 180,000
AI Inference Engineer
AI Inference Engineer

Next Ventures • Amsterdam

Hybrid
EUR 120,000 - 180,000
Hybrid work model
Senior AI Inference Engineer
Senior AI Inference Engineer

Empiric • Amstelveen

On-site
EUR 90,000 - 130,000
Senior Open-Weight LLM Engineer — Remote & Production
Senior Open-Weight LLM Engineer — Remote & Production

EverAI • Nederland

Remote
EUR 75,000 - 125,000
MLOps Engineer
MLOps Engineer

EPAM Systems • Netherlands

Hybrid
EUR 85,000 - 120,000
Senior AI Engineer I — Remote, Scalable AI Solutions
Senior AI Engineer I — Remote, Scalable AI Solutions

Vacaturebank • Netherlands

Remote
EUR 90,000 - 150,000
Remote work flexibility
Competitive salary
Comprehensive benefits
+1