RAG Engineer
Engineeringfull timeRemotemid level$75k-$115k
About This Role
We're seeking a RAG Engineer to design and optimize Retrieval-Augmented Generation systems that power our AI-first recruiting platform. You'll build scalable pipelines that integrate semantic search, vector databases, and LLMs to deliver intelligent candidate matching and talent insights. This role is critical to enhancing our core product's AI capabilities and directly impacts how recruiters discover and engage top European talent.
Requirements
- Design and implement end-to-end RAG pipelines for production systems
- Optimize retrieval quality through fine-tuning embeddings and ranking algorithms
- Work with vector databases and implement efficient similarity search
- Integrate large language models (LLMs) into application workflows
- Write clean, testable Python code with strong documentation practices
- Collaborate with product and data teams to define retrieval requirements
Skills
Retrieval-Augmented Generation (RAG)Vector Databases (Pinecone, Weaviate, Milvus)LLM Integration (OpenAI, Anthropic, Llama)PythonSemantic SearchPrompt EngineeringInformation RetrievalFastAPI / REST APIs
