AI Scientist (Agentic AI)
Role details
Job location
Tech stack
Job description
AI with real-world actions, and judge models that validate outputs. Your work won't sit in research notebooks - it'll ship. The Agentic AI team is building the next generation of AI-native products - intelligent systems that reason, act, and adapt. We combine the power of large language models (LLMs), autonomous agents, and retrieval-augmented generation (RAG) to move beyond static prompts and chatbots into dynamic AI systems that solve real problems at scale. We don't treat LLMs as tools to micromanage - we treat them as collaborators. Our products are designed to build and evolve themselves, leveraging AI to orchestrate workflows, make decisions, and continuously improve. If you're ready to stop building brittle bots and start building AI that builds AI - this is your playground. - Architect and deploy agent-based systems using LangGraph, PydanticAI, LangChain, Google ADK, Claude SDK, or custom-built orchestration frameworks - Build and optimize RAG pipelines - from smart chunking to embedding strategies and vector search - Design self-evolving prompt systems and dynamic decision flows driven by LLMs - Develop APIs and services that let models talk to tools, data, and other systems - Monitor, evaluate, and automate model feedback loops using AI-based simulation and testing agents - Work cross-functionally with product and engineering teams to ship AI-native features, not just prototypes Qualifications - 2+ years of experience in applied AI/ML engineering with real-world deployments - Strong Python skills and experience with 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 - You take ownership. If something is unclear or blocked, you figure it out or find a way around it. - You move fast but don't cut corners - you care about quality and
Requirements
impact. - You believe working code beats perfect plans, and that iteration is the fastest way to clarity. Nice to have: - Open-source model experience (e.g., LLaMA2, Mixtral, Mistral) or custom inference stacks - Judge models, feedback loops, or human-in-the-loop architecture - Experience designing test harnesses using agent personas or synthetic users - Familiarity with prompt injection mitigation, output validation, or agent safety - Background in shipping AI inside real-world web or mobile products Additional Information Ensuring you and all our Heroes are looked after, happy, and healthy is always on the menu. Because if you're in good shape, then we're in good shape. - Make the most of our hybrid working model and join the team for face-to-face connection and collaboration in our beautiful Berlin campus 2 days a week - We offer 27 days holiday with an extra day on 2nd and 3rd year of service - We will support you in developing
Benefits & conditions
yourself and your career growth opportunities: 1.000 € Educational Budget, Language Courses, Parental Support and access to the Udemy Business platform to explore a variety of online courses. - Get moving and release those wonderful, mind-boosting endorphins: Health Checkups, Meditation, Yoga, Gym & Bicycle Subsidy - Cash. Dough. Cheddar. Whatever you call it, we'll help you with it: Employee Share Purchase Plan, Sabbatical Bank, Public Transportation Ticket Discount, Life & Accident Insurance, Corporate Pension Plan - The power of getting together over some food is unrivaled. Here are a few ways to help you do that. All the yum: Digital Meal Vouchers, Food Vouchers, Corporate Discounts. Courses. Ready to join our team? If you're excited to grow, collaborate and be part of the world's leading delivery platform, we'd love to hear from you. Apply today! We believe diversity and inclusion are key to creating not only an exciting product, but also an amazing
