Remote Inference & Model Quality Engineer — Dutch Models

HostYourAI; United States; Remote; USD 150,000 - 210,000; Full time

Benefits offered by this job

Remote work

HQ Groningen

Team weeks abroad

Top of market salary

Job summary

HostYourAI is seeking an engineer to help run open language models efficiently on GPU infrastructure and to establish a consistent way to measure their quality. The role covers model serving, performance and cost tuning, evaluation, and improvements to an in-house Dutch model with results documented for users and regulatory transparency.

You will deploy and operate models on GPUs using serving frameworks such as vLLM, assess hardware fit and cost, benchmark performance, and build an evaluation

Qualifications

• Experience serving models on GPUs or fine-tuning language models.
• Knowledge of SFT, DPO, or LoRA and related model-serving tools.
• Proficiency with Python, Linux, containers, and ML libraries like Hugging Face or PyTorch.
• Fluent English and ability to work independently.

Responsibilities

• Deploy and operate models on GPUs using serving frameworks such as vLLM.
• Assess hardware fit and serving cost through VRAM estimates, quantization, and related trade-offs.
• Benchmark throughput and latency, then improve performance and cost per token.
• Build a shared evaluation harness covering quality, Dutch-language ability, grounding, tool use, and speed.
• Create datasets, run fine-tuning experiments, and compare new model versions against prior ones.
• Publish model cards and benchmarks, including required AI Act transparency information.

Skills

GPU serving

Fine-tuning LM

Benchmarking

Python

Linux

Containers

Hugging Face

PyTorch

English fluency

Tools

vLLM

SGLang

LoRA

SFT

DPO

Job description

HostYourAI is seeking an engineer to help run open language models efficiently on GPU infrastructure and to establish a consistent way to measure their quality. The role covers model serving, performance and cost tuning, evaluation, and improvements to an in-house Dutch model with results documented for users and regulatory transparency.

You will deploy and operate models on GPUs using serving frameworks such as vLLM, assess hardware fit and cost, benchmark performance, and build an evaluation