Stellenbeschreibung:

We're Hiring: RAG Engineer / LLM Applications Developer (Remote | Freelance)

We're looking for an experienced RAG Engineer or LLM Applications Developer who’s passionate about building intelligent systems that combine retrieval and generation. If you've been working with tools like LangChain, HuggingFace, or OpenAI APIs and understand how to turn LLMs into production-grade applications—this is for you.


What you’ll work on:
• Building intelligent apps using Python and transformer models (GPT, Claude, LLaMA)
• Designing semantic search pipelines and hybrid retrieval systems
• Working with vector databases (Pinecone, Weaviate, Chroma, FAISS)
• Integrating LangChain, LlamaIndex, Streamlit, or similar tools into scalable solutions
• Fine-tuning prompts and optimizing RAG workflows


Must-haves:
• Strong Python programming skills and experience working with LLMs
• 3+ years working with at least 2 of the following: LangChain, LlamaIndex, HuggingFace, OpenAI API, Streamlit
• Strong grasp of prompt engineering, embeddings, TF-IDF, and similarity metrics


Nice to have:
• Experience in indexing and chunking document embeddings
• Building modular RAG pipelines
• Optimizing context windows, latency, and cost
• Observability (e.g., Arize Phoenix), chatbot UX, or domain-specific implementations (finance, healthcare)


Work Setup:
• Freelance / contract
• 100% remote
• Flexible timezone collaboration


If you’re ready to take your GenAI engineering skills to the next level, send us your CV and let’s connect!

NOTE / HINWEIS:

EN: Please refer to Fuchsjobs for the source of your application

DE: Bitte erwähne Fuchsjobs, als Quelle Deiner Bewerbung