Requirements

Expected technologies

Python

Elasticsearch

Agentic Architectures

RAG

LangGraph

LangFuse

Vector Database

Optional technologies

React.js

TypeScript

Node.js

Event-Driven Architecture

MongoDB

Operating system

macOS

Our requirements

• Experience: 5+ years of hands-on experience as a Software Engineer or similar role, including a minimum of 2 years dedicated to building and deploying AI/ML applications.
• Core Technical Expertise:
• Programming Language: Proficiency in Python for developing scalable backend and AI services.
• Generative AI Architectures: Strong experience in designing, implementing, and productionizing RAG systems and Agentic Architectures.
• AI Engineering: Proven ability to apply principles like Prompt Engineering or Context Engineering to achieve desired AI application behaviors.
• Orchestration & Observability: Strong practical experience with AI orchestration frameworks (LangGraph) and AI tracing/monitoring tools (Langfuse).
• Search Engines: Proven hands-on experience implementing and managing high-performance search solutions using engines like Elasticsearch, leveraging knowledge of various search techniques (semantic, lexical, etc.)
• Databases: Hands-on experience working with Vector Databases such as Qdrant and non-relational databases like MongoDB.
• Software Engineering: Solid understanding of software design patterns, API development, and Git version control.
• General Requirements:
• Agile Development: Experience working in Agile environments (Scrum, Kanban) with tools like Jira, Confluence.
• Communication: Strong interpersonal skills with professional-level English proficiency.
• Mindset: Passion for delivering high-quality, intelligent, and useful applications to the end-user.

Optional

• Full Stack Development: Familiarity with the TypeScript, Node.js, or React ecosystem (to ease API integration).
• Cloud & Deployment: Familiarity with DevOps practices, CI/CD pipelines, and cloud platforms (Azure, AWS).
• Event-Driven Architecture: Hands-on experience in data streaming technologies (e.g., Apache Kafka).
• Domain Knowledge: Prior experience in the IoT or smart home technology sector.
• Language Skill: Proficiency in German.

Your responsibilities

• Architect AI Systems: Design, develop, and deploy production-ready GenAI and Agent Solutions using orchestration frameworks like LangGraph to automate complex user interactions and challenging workflows.
• Optimize AI Performance: Evaluate, measure and improve our AI solutions across all dimensions: quality, speed, cost and quotas.
• LLM Interactions: Master Prompt and Context Engineering to precisely govern LLM reasoning, behavior, and final output quality. This work directly ensures the system's reliability, safety, and efficiency, while minimizing operating cost and latency under production load.
• Information Retrieval: Engineer advanced retrieval systems, utilizing various search techniques such as full-text search, vector search, and hybrid search on search engines like Elasticsearch to feed the AI the most relevant data for highly accurate, context-aware, and timely responses.
• LLM Interactions: Master Prompt and Context Engineering to precisely govern LLM reasoning, behavior, and final output quality. This work directly ensures the system's reliability, safety, and efficiency, while minimizing operating cost and latency under production load.
• Information Retrieval: Engineer advanced retrieval systems, utilizing various search techniques such as full-text search, vector search, and hybrid search on search engines like Elasticsearch to feed the AI the most relevant data for highly accurate, context-aware, and timely responses.
• Ensure AI Observability: Integrate and utilize AI application monitoring tools, particularly Langfuse, to observe, trace, evaluate, and continuously improve agent performance and RAG quality.
• Ensure Platform Stability: Apply load balancing and scaling techniques to handle real-world load across LLM deployments and computational resources.
• Code Quality & Ownership: Write clean, production-ready, scalable, and well-tested code in Python, including testing the AI logic end-to-end.
• Collaborate & Lead: Work closely with product managers and cross-functional engineering teams to guide technical decisions and translate abstract AI concepts into deployed, impactful features.