Назад
Company hidden
обновлено 9 часов назад

LLM Engineer — Post-Training (Remote - Netherlands)

75 000 - 125 000€
Формат работы
remote (только Europe)
Тип работы
fulltime
Грейд
senior
Английский
b2
Страна
Portugal/Netherlands
Вакансия из списка Hirify.GlobalВакансия из Hirify Global, списка международных tech-компаний
Для мэтча и отклика нужен Plus

Мэтч & Сопровод

Для мэтча с этой вакансией нужен Plus

Описание вакансии

Текст:
/
TL;DR
LLM Engineer — Post-Training (AI): Fine-tuning self-hosted open-weight language models and shipping improved model behavior for a consumer AI companionship platform with an accent on SFT, LoRA/QLoRA, DPO, GRPO, data, and evaluations. Focus on diagnosing model failures, improving personalization and multilingual behavior, accelerating reproducible training cycles, and using real user behavior to guide production iterations.

Location: Remote; listed locations are the Netherlands and Portugal. The role is also described as fully remote and work-from-anywhere.

Salary: €75K–€125K per year.

Company

hirify.global develops AI companionship products for more than 60 million users, supported by its proprietary EverGuard moderation system.

What you will do

  • Fine-tune self-hosted, open-weight LLMs using SFT, LoRA/QLoRA, DPO, GRPO, and other post-training methods.
  • Diagnose model failures and determine whether to address them through data, post-training, prompting, or classifiers.
  • Build training data and evaluations that guide subsequent model development.
  • Improve personalization, character consistency, tone, multilingual behavior, and group interactions.
  • Ship models to production and use real user behavior to guide further iterations.
  • Accelerate the training loop through faster, easier-to-compare, and more reproducible experiments.

Requirements

  • Personally post-trained open-weight LLMs for a user-facing product and shipped them to production.
  • Worked on a product or business where AI was core, rather than an experimental side feature.
  • Fine-tuning is a core part of professional experience.
  • Strong Python, PyTorch, and Hugging Face skills, including hands-on GPU training and debugging.
  • Build data and evaluations independently and make decisions based on evidence.
  • Can take work beyond notebooks into production.
  • Use AI tools daily in engineering work.
  • Fully comfortable working with uncensored models and explicit NSFW content, including harmful material, when developing and evaluating the moderation system.

Nice to have

  • Experience with conversational AI, roleplay products, or highly personalized consumer AI.
  • Experience with multilingual LLMs, moderation, safety, or adversarial testing.
  • Experience with multimodal models.
  • Open-source LLM or post-training contributions.

Culture & Benefits

  • Fully remote team with an annual in-person gathering.
  • B2B contract is preferred, with flexibility for a long-term commitment.
  • 20 working days of paid time off per year.
  • Monthly health-insurance allowance of 100 USD and access to unlimited one-to-one sessions with psychologists and lifestyle experts.
  • Co-working budget of up to two visits per month, plus learning, equipment, and AI-tool budgets.

Будьте осторожны

Если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого. Это мошенники. Обязательно жмите «Пожаловаться» или пишите в поддержку. Подробнее в гайде →