Context Engineer Loes

HostYourAI

Nederland

Hybrid

EUR 70,000 - 100,000

Full time

14 days+

A complete application in a minute

Tailored resume and cover letter, ready to send.

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

We run open models on GPUs across Europe and are building our own Dutch model, Loes. You make sure those models run fast, reliably and affordably, and that we know how good each model really is.

What you'll do
  • Get models running, and keep them running, on our GPUs: vLLM now, SGLang next. Figure out what fits where and at what price, from VRAM estimates to quantization.
  • Measure and improve throughput and latency, and keep the cost per token sharp.
  • Build an eval harness that holds every model we host to the same standard: quality, Dutch, grounding, tool calling, speed.
  • Make Loes better: build datasets, run finetunes and measure whether a new version really beats the previous one.
  • Publish model cards and benchmarks, including the transparency information the AI Act requires per model.
What we ask
  • Experience running models on GPUs (vLLM, SGLang or similar), training or finetuning language models (SFT, DPO, LoRA), or both.
  • You measure instead of trusting your gut: benchmarks, evals, and statistics where needed.
  • Python, Linux and containers, and the usual tooling around them (Hugging Face, PyTorch). You don't need to know everything, learning fast is what counts.
  • Fluent English. Dutch is a genuine plus, because you judge the quality of Loes most sharply in your own language. You must be based in the Netherlands.
  • Independent. There's no manager spelling out your work for you.
What we offer
  • A competitive salary at the top of the market.
  • Remote work, with our HQ in Groningen. Twice a year the whole team spends a week abroad together.
  • A spot on the first team of a startup, with all the room and responsibility that comes with it. And above all: the chance to be part of this journey from the very start.
Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

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

HostYourAI • Nederland

Hybrid
EUR 70,000 - 100,000
Medior AI Engineer / Developer (Full-Stack)
Medior AI Engineer / Developer (Full-Stack)

Combler.AI • Eindhoven

Hybrid
EUR 65,000 - 90,000
Hybrid work model
Pension scheme
Annual learning budget
+1
MLOps Engineer
MLOps Engineer

EPAM Systems Inc • Rijswijk

Hybrid
EUR 85,000 - 110,000
26 paid holidays
Pension plan
Disability insurance
+8
MLOps Engineer
MLOps Engineer

EPAM Systems Inc • Amsterdam

Hybrid
EUR 80,000 - 110,000
26 paid holiday days
Pension plan scheme
Disability insurance
+7
MLOps Engineer
MLOps Engineer

EPAM Systems • Amsterdam

Hybrid
EUR 90,000 - 120,000
26 paid holiday days
Pension plan scheme
Disability insurance (WGA)
+7
MLOps Engineer
MLOps Engineer

EPAM Systems • Rijswijk

Hybrid
EUR 80,000 - 110,000
Holiday entitlement 26 days
Pension plan scheme
Disability insurance (WGA)
+7
Forward Deployed Engineer Manager
Forward Deployed Engineer Manager

Sia • Maastricht

Hybrid
EUR 110,000 - 150,000
Hospital insurance
Performance-related bonus
Learning budget
+1
Full Stack Engineer
Full Stack Engineer

Engaige • Utrecht

Hybrid
EUR 90,000 - 130,000
Stock options
Growth opportunities toward CTO
MLOps Engineer
MLOps Engineer

EPAM Systems • Netherlands

Hybrid
EUR 85,000 - 120,000
Forward Deployed Engineer Manager
Forward Deployed Engineer Manager

Sia Partners • Maastricht

Hybrid
EUR 90,000 - 140,000
Hospital insurance
Learning budget and partner trainings
Hybrid work from Amsterdam office
+1