We are seeking a forward-thinking AI Developer to design, implement, and scale autonomous, goal-driven AI systems capable of decision-making, multi-step planning, collaboration, and continuous improvement. 

This role is ideal for someone passionate about AI solutions/architectures, prompt engineering, and modular AI workflow orchestration, with hands-on experience building production-ready AI agents that interact with tools, data, and real-world systems. 

Although the role is remote-first, the position requires a few mandatory in-office days per month in Basel (Switzerland) 

🔧 Requirements (Must-Have) 

• 3+ years of experience in software development or applied AI. 

• Strong Python proficiency with experience in agent frameworks such as LangChain, DSPy, AutoGen, CrewAI, or equivalent systems. 

• Deep understanding of agent design patterns, including planner/executor, memory/reflection loops, tool selection, and self-evaluation. 

• Expertise in prompt engineering, including chain-of-thought, ReAct, structured prompting, and output validation. 

• Experience building RAG systems, including chunking strategies, embedding optimization, and retrieval tuning. 

• Hands-on experience with vector databases (FAISS, Pinecone, Weaviate, OpenSearch). 

• Experience deploying and integrating LLMs via APIs (OpenAI, Anthropic, Cohere) and open-source models (LLaMA, Mistral, Qwen, DeepSeek). 

• Familiarity with LLM serving and inference frameworks such as vLLM, TGI, or Ollama. 

• Experience with tool integration, including REST APIs, file systems, databases, and browser automation. 

• Solid understanding of Docker, Git, and basic cloud infrastructure (AWS, GCP, Azure). 

• Strong command (B2-C1) in English and German. 

📓Key Responsibilities 

• Architect and build agentic AI systems using frameworks such as LangChain, AutoGen, DSPy, CrewAI, or custom-built orchestration tools. 

• Design modular, goal-oriented workflows enabling autonomous agents to plan tasks, collaborate with other agents, and interact with external tools. 

• Implement planner–executor, ReAct, reflection, and self-verification agent patterns. 

• Develop advanced prompting strategies, including chain-of-thought, tree-ofthought, structured outputs, and prompt versioning. 

• Build and integrate memory systems (short-term, long-term, episodic) to support context persistence and learning. 

• Integrate LLMs (OpenAI, Anthropic, Mistral, Cohere, DeepSeek, opensource models) with execution environments such as Python, Bash, SQL, REST APIs, and browser automation tools. 

• Implement tool calling / function, API orchestration, and code execution agents. 

• Design and optimize Retrieval-Augmented Generation (RAG) pipelines using vector databases and hybrid search. 

• Optimize agent performance for latency, reliability, cost efficiency, and scalability in real-world applications such as research agents, coding copilots, and planning assistants. 

• Deploy and maintain agentic systems in production using Docker, CI/CD pipelines, and cloud infrastructure. 

• Monitor agent behavior, log execution traces and reasoning steps (where  appropriate), and continuously improve system robustness and alignment. 

• Collaborate closely with data scientists, software engineers, product teams, and UX designers to deliver high-impact AI solutions. 

• Implement human-in-the-loop workflows for oversight, feedback, and safe autonomy.