About the Company
We are a Swedish AI-startup building a next-generation creation layer that converts natural-language intent into governed, portable systems — producing APIs, UIs, tests, and deployment artifacts automatically and extremely efficiently.
Overview:
We are seeking an AI Engineer to develop the application layer of our answer engine. This role focuses on designing and building robust Retrieval-Augmented Generation (RAG) pipelines and agentic workflows capable of reasoning, verifying facts, and handling complex queries with minimal hallucination. You will directly contribute to building AI systems that are reliable, accurate, and production-ready.
Key Responsibilities:
- Create RAG systems using LangChain or LangGraph, managing context windows and retrieval relevance.Implement hybrid search strategies using vector stores ( pgvector,qdrant) and re-ranking models.
- Build agentic tools (web search, code execution) with robust error handling and state management.
- Develop evaluation loops to verify citation accuracy and answer relevance.
Qualifications:
- Strong experience building RAG pipelines and working with vector databases (pgvector, Qdrant, Pinecone, etc.).
- Familiarity with LangChain, LangGraph, or similar frameworks.
- Proficient in Python and building production-grade AI applications.
- Experience with agentic AI tools, multi-step reasoning workflows, and error/state management.
- Strong analytical skills and experience designing evaluation metrics for AI systems.
Preferred:
- Familiarity with LLMs for reasoning and generation tasks.
- Experience with hybrid search, re-ranking models, and context management for retrieval systems.