aillmragprompt engineeringembeddingssemantic searchagentic aievaluation frameworksspeech ai
Вакансия из Hirify Global, списка международных tech-компаний Для мэтча и отклика нужен Plus
Пожаловаться
Зарплата и рынок
ЗП не указанаразвернуть
На похожих ролях по рынку
$78к$101кмедиана$144к
38 в выборке
На СНГ рынке: $4.4к/мес ($3.7к - $5.6к)
91
Крутая вакансия
развернуть
Чёткая ответственность за AI-функции в работающем продукте сочетается с автономией и заметными льготами; в небольшой команде процессы и системы ещё могут формироваться.
?Небольшая команда
Актуальные AI-задачи
Устойчивый продукт
Щедрые условия
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
AI Engineer (LLMs/RAG): Building production AI features that turn conversations into intelligence through summaries, semantic search, memory, and automated actions with an accent on prompt engineering, retrieval systems, and evaluation quality. Focus on designing reliable AI infrastructure, optimizing provider routing and latency, and shipping agentic workflows that solve real user problems.
Location: Barcelona, Spain; hybrid setup with regular collaboration at the Barcelona office
Company
hirify.global is a profitable, bootstrapped AI company building a multilingual transcription platform and new conversation-intelligence products.
What you will do
Own AI features end-to-end, from problem discovery and prompt design through production, including summaries, search, actions, and memory.
Build and maintain evaluation frameworks that detect quality regressions and support confident prompt iteration.
Optimize AI infrastructure for speed, cost, and reliability through provider routing, caching, chunking, and latency management.
Evaluate new models and techniques, deciding when migrations are worth the cost.
Collaborate with product designers and engineers to integrate AI features into the product.
Build semantic transcript search, agentic workflows for meeting follow-ups, and prompt evaluation pipelines.
Requirements
5+ years of engineering experience, including 2+ years focused on AI applications.
Experience shipping LLM-based features to production for real users.
Fluency in prompt engineering, RAG architectures, and evaluation frameworks.
Experience debugging retrieval quality and hallucinating prompts.
Ability to make trade-offs between latency, quality, cost, capability, speed of delivery, and technical debt.
Product-minded approach focused on solving user problems and discontinuing ineffective features.
Alignment with the company’s engineering principles and most of the Rails doctrine.
Nice to have
Experience shipping AI features in B2B SaaS where reliability and accuracy are important.
Experience building multi-provider LLM systems with fallbacks, routing, and cost optimization.
Experience designing retrieval systems at scale, including embeddings, reranking, and hybrid search.
Experience with speech or audio AI, such as transcription, diarization, or real-time processing.
Culture & Benefits
Trust-based culture with autonomy and independence.
Hybrid work with a Barcelona office in Gràcia, flexible working hours, and protected focus time.
International, English-fluent working environment.
Competitive salary positioned in the top percentiles of the Barcelona startup scene and equity.
Generous AI token spending policy, 30 days of holiday allowance, and health coverage through Alan covering half of medical insurance.
Tax-smart savings through Cobee by Pluxee for meals, transport, and nursery expenses.
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 →