aipythonllmpytorchfine tuningsftlorahuggingfacedpoqloragrpogpu training
Вакансия из Hirify Global, списка международных tech-компаний Для мэтча и отклика нужен Plus
Пожаловаться
Зарплата и рынок
развернуть
€75к-125к/год
€64к€100кмедиана€130к
По похожим ролям (42) ~ €100к/год
На СНГ рынке: $4.4к/мес ($3.7к - $5.9к)
86
Хорошая вакансия
развернуть
Это чётко очерченная роль с фокусом на запуск LLM в продукте быстрорастущей AI-компании, но работа предполагает регулярный контакт с откровенным и потенциально вредным контентом.
Сложный контент
Чёткие задачи
Современный стек
AI-продукт с масштабом
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
LLM Engineer (Post-Training) (SFT/DPO/GRPO): Fine-tuning and shipping open-weight LLMs for a large-scale AI companionship platform with an accent on model behavior, personalization, multilingual performance, and production quality. Focus on diagnosing model failures, building training data and evaluations, accelerating reproducible training cycles, and improving models through real user behavior.
Location: Remote; the position is listed for Italy and Portugal, with a fully remote work arrangement and an annual in-person meetup.
Salary: €75K–€125K per year.
Company
hirify.global develops AI companionship products, including a large-scale AI companionship platform and EverGuard, a proprietary AI 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 datasets 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 iterations.
Improve training speed, experiment comparison, and reproducibility.
Requirements
Personal experience post-training open-weight LLMs for a user-facing product and shipping them to production.
Experience working where AI was core to the product or business, with fine-tuning as a central part of the work.
Strong Python, PyTorch, and Hugging Face skills, including hands-on GPU training and debugging.
Ability to build datasets and evaluations independently and make evidence-based decisions.
Ability to take work beyond notebooks into production.
Daily use of AI tools in engineering work.
Comfort working with uncensored models and explicit NSFW content, including harmful material, when developing and evaluating moderation systems.
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 work with a culture of ownership, velocity, and radical creativity.
B2B contract preferred, with flexibility for a long-term commitment.
20 working days of paid time off per year.
Annual in-person team gathering.
USD 100 monthly health-insurance allowance and access to unlimited one-to-one sessions with psychologists and lifestyle experts.
Co-working, learning, equipment, and premium AI-tool budgets, including ChatGPT, Hugging Face, and Claude Code.
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 →