LLM Application Engineer

XpertDirect; Stockholms kommun; On-site; SEK 700,000 - 900,000; Full time

Job summary

XpertDirect in Sweden is seeking an LLM Application Engineer to build practical AI applications that help people find information, automate workflows, and work more effectively with enterprise data.

You’ll work across Python, LLMs, RAG, APIs, and vector search, taking AI features from early prototypes through to reliable production applications. This role collaborates with Product, Backend and Data teams to translate business requirements into scalable AI solutions.

Qualifications

• 3+ years in Software Engineering, AI Engineering, ML Engineering, or a similar role.
• Experience with FastAPI or similar backend frameworks.
• Experience building production software or AI applications.

Responsibilities

• Build production LLM applications in Python.
• Develop RAG systems connecting LLMs with enterprise knowledge and data.
• Build backend services and APIs using FastAPI.
• Integrate commercial and open-source LLM APIs.
• Implement semantic search using vector databases.
• Design document ingestion, chunking, embedding, and retrieval workflows.
• Build AI-powered knowledge search and intelligent assistant features.
• Develop workflow automation using LLM capabilities.
• Work with structured application data in PostgreSQL.
• Containerise services and applications using Docker.
• Evaluate and improve response quality, retrieval relevance, and latency.
• Integrate AI features with existing enterprise APIs and software products.
• Collaborate with Product, Backend, and Data teams to turn business requirements into working AI solutions.

Skills

Software Engineering

AI Engineering

ML Engineering

Tools

FastAPI

Python

APIs

Vector search

Job description

Enterprise Software | Generative AI | LLM Applications | RAG | Applied AI

We're looking for an LLM Application Engineer to build practical AI applications that help people find information, automate workflows, and work more effectively with complex enterprise data.

You'll work across Python, LLMs, RAG, APIs, and vector search, taking AI features from early prototypes through to reliable production applications.

What You’ll Work On

• Build production LLM applications in Python
• Develop RAG systems connecting LLMs with enterprise knowledge and data
• Build backend services and APIs using FastAPI
• Integrate commercial and open-source LLM APIs
• Implement semantic search using vector databases
• Design document ingestion, chunking, embedding, and retrieval workflows
• Build AI-powered knowledge search and intelligent assistant features
• Develop workflow automation using LLM capabilities
• Work with structured application data in PostgreSQL
• Containerise services and applications using Docker
• Evaluate and improve response quality, retrieval relevance, and latency
• Integrate AI features with existing enterprise APIs and software products
• Collaborate with Product, Backend, and Data teams to turn business requirements into working AI solutions

Core Skills

• 3+ years in Software Engineering, AI Engineering, ML Engineering, or a similar role
• FastAPI or similar backend frameworks
• Experience building production software or AI applications