Назад
Company hidden
2 дня назад

Senior AI Scientist (Agentic AI)

Формат работы
hybrid
Тип работы
fulltime
Грейд
senior
Английский
b2
Страна
Germany
Релокация
Germany
Вакансия из списка Hirify.GlobalВакансия из Hirify RU Global, списка компаний с восточно-европейскими корнями
Для мэтча и отклика нужен Plus

Мэтч & Сопровод

Для мэтча с этой вакансией нужен Plus

Описание вакансии

Текст:
/

TL;DR

Senior AI Scientist (Agentic AI): Architecting and deploying agent-based systems for AI-native products using LLMs, autonomous agents, and RAG with an accent on dynamic orchestration, self-evolving prompts, and real-world actions. Focus on building RAG pipelines, APIs for tool integration, and AI-driven feedback loops to create adaptive systems that solve problems at scale.

Berlin, Germany (hybrid: 2 days/week in Berlin office). Relocation to Berlin supported.

Company

World’s pioneering local delivery platform operating in 65+ countries, headquartered in Berlin, listed on Frankfurt Stock Exchange.

What you will do

  • Architect and deploy agent-based systems using LangGraph, PydanticAI, LangChain, or similar frameworks
  • Build and optimize RAG pipelines including chunking, embeddings, and vector search
  • Design self-evolving prompt systems and dynamic LLM-driven decision flows
  • Develop APIs and services enabling models to interact with tools and data
  • Monitor, evaluate, and automate model feedback using AI-based simulations
  • Collaborate with product and engineering teams to ship production AI features

Requirements

  • 2+ years in applied AI/ML engineering with real-world deployments
  • Strong Python and frameworks like LangChain, LlamaIndex, or Haystack
  • Deep knowledge of RAG, LLM mechanics, prompt design, and chaining
  • Experience with vector databases (Pinecone, Weaviate, FAISS) and embedding models
  • Ownership mindset: figure out blocks and deliver quality working code iteratively

Nice to have

  • Open-source models (LLaMA2, Mixtral, Mistral) or custom inference
  • Judge models, feedback loops, human-in-the-loop architecture
  • Test harnesses with agent personas or synthetic users
  • Prompt injection mitigation, output validation, agent safety
  • Shipping AI in web or mobile products

Culture & Benefits

  • Hybrid model: 2 days/week in Berlin campus for collaboration
  • 27+ days holiday, increasing with tenure
  • €1,000 educational budget, language courses, Udemy, parental support
  • Health checkups, gym/bicycle subsidy, meditation
  • Employee share plan, sabbatical bank, public transport discount, pension, insurance
  • Meal vouchers, food discounts, relocation support to Berlin

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 →