AI Engineer

KI group GmbH; München; Vor Ort; EUR 50.000 - 90.000; Vollzeit

Zusammenfassung

Ein innovatives Unternehmen sucht einen AI Engineer, der an der Spitze der KI-Entwicklung arbeitet. In dieser spannenden Rolle werden Sie mit erfahrenen Ingenieuren und Forschern zusammenarbeiten, um intelligente Systeme zu entwerfen und zu implementieren, die in Unternehmensumgebungen agieren, planen und lernen. Sie werden die Möglichkeit haben, agentische Workflows zu erstellen, die reale Aufgaben durch die Koordination von Tools und APIs lösen. Wenn Sie eine Leidenschaft für Technologie haben und in einem dynamischen Umfeld arbeiten möchten, ist dies die perfekte Gelegenheit für Sie.

Leistungen

Mentorship von Weltklasse-Ingenieuren

Mitarbeit in einem kleinen, schnelllebigen Team

Vertrauen in Ihre Ideen und Einflussnahme

Arbeiten an der Spitze der KI-Anwendungen

Qualifikationen

• Erfahrung in Python und LLMs ist erforderlich.
• Vertrautheit mit Orchestrierungstools für LLM-Ketten ist von Vorteil.

Aufgaben

• Entwickeln und Implementieren von intelligenten Systemen für Unternehmen.
• Prototyping und Aufbau agentischer Systeme mit LLMs.

Kenntnisse

Python

LLMs (OpenAI, Hugging Face)

JSON

APIs

Task orchestration logic

Startup mindset

Tools

LangChain

CrewAI

AutoGen

FastAPI

Flask

Docker

Vector databases (Weaviate, Pinecone, FAISS)

Jobbeschreibung

About us:

Our mission is to supercharge IT enterprise organizations with custom AI solutions. Headquartered in the heart of Munich with a hub in Lisbon, we’re a team of builders, dreamers, and problem-solvers tackling some of the most exciting and complex challenges in AI native development adoption.

We operate on speed, adaptability, and extreme ownership. That means we move fast, stay flexible, and take full responsibility for our impact. Our clients trust us because we don’t ship generic tools — we embed AI into real-world enterprise workflows with precision and empathy.

What You’ll Do:

As a AI Engineer, you’ll work alongside experienced engineers and researchers to design and implement intelligent systems that act, plan, and learn in enterprise environments. You’ll contribute to building agentic workflows — autonomous or semi-autonomous AI agents that complete real-world tasks by coordinating tools, APIs, and reasoning steps.

• Collaborate with the team to prototype and build agentic systems powered by LLMs and retrieval-augmented generation (RAG).

• Help design agents that can interact with enterprise tools (Jira, Notion, internal APIs, etc.) to solve specific user problems.

• Implement tools and frameworks to chain LLM calls, maintain memory/state, and handle multi-turn interactions.

• Support training, fine-tuning, and evaluation of LLMs on internal and client datasets.

• Write production-ready code and contribute to robust backend systems that support real-time AI workflows.

• Document your experiments, communicate tradeoffs, and be involved in making technical decisions.

What We’re Looking For:

We don’t expect you to know everything — but we do expect you to learn fast and be ready to get your hands dirty.

Must-Haves:

• Solid programming skills in Python or similar and experience working with LLMs (OpenAI, Hugging Face, etc.).

• Familiarity with tools for orchestrating LLM chains or agents (LangChain, CrewAI, AutoGen, or similar).

• Curiosity and understanding of how agents can interact with tools and external APIs to complete multi-step tasks.

• Comfortable working with JSON, APIs, and task orchestration logic.

• A startup mindset — eager to experiment, build, and iterate quickly in uncertain environments.

Nice-to-Haves:

• Experience with vector databases (like Weaviate, Pinecone, or FAISS) or RAG pipelines.

• Exposure to prompt engineering and function calling with modern LLM APIs.

• Experience deploying backend services (FastAPI, Flask) or using Docker.

• Side projects, GitHub contributions, or open-source involvement in the AI space.

Why Join Us:

• Work at the bleeding edge of AI applied to real enterprise use cases.

• Be part of a small, fast-moving team where your voice matters.

• Get mentorship from world-class engineers and researchers.

• Shape the future of AI-native software inside real organizations.

• We value ownership — you’ll be trusted to run with your ideas and drive impact.