Experienced AI Engineer

About the position

Join MicroTech Software to build cutting-edge AI-powered tools for insurance professionals. Work on production RAG chatbots, agentic workflows, and voice-to-workflow capabilities.

At MicroTech Software we build cutting edge AI-powered tools that help insurance professionals answer complex questions faster and with greater confidence. Our flagship product is a production RAG chatbot used daily by insurance workers, and we are actively pushing its architecture in several new directions at once using the newest models. Your reference will be our AI Lead. We are looking for an engineer with 2–4 years of experience who has reached the point where writing good code is no longer the hard part — and who is ready to take on the harder questions: which approach to use, how to structure a system for long-term maintainability, and where to invest engineering time to get the most impact. You will work in a team with a very advanced team lead whom you can expect to learn from and alongside one or more junior engineers and be expected to help set the direction of their work as well as your own.

Responsibilities

Shape the architecture of a live AI product

Evaluate and challenge design decisions across the stack — retrieval strategies, LLM backend selection, service boundaries, data flow — and propose improvements with clear reasoning

Participate in technical planning with the team and with insurance-domain stakeholders, translating vague requirements into concrete engineering tasks

Identify technical debt, assess its cost, and make the case for addressing it

Navigate an on-prem transition

Design and lead the migration of a cloud-dependent LLM stack to a fully local alternative: self-hosted models, local embedding, and on-prem vector stores

Evaluate open-weight LLMs for Danish-language RAG quality; understand the trade-offs in latency, accuracy, and hardware requirements

Contribute to a RAG → GraphRAG transition: build a knowledge graph and integrate it into an existing RAG pipeline

Design and build agentic workflows

Design multi-step agent architectures using LangGraph or equivalent frameworks that can route, plan, use tools, and synthesize across document corpora

Define tool-use interfaces, memory patterns, and failure handling strategies for agent loops running in production

Work with domain experts to identify automation opportunities worth building

Enable voice-to-workflow capabilities

Contribute to the design of a pipeline that integrates local speech-to-text models into agentic workflows

Evaluate Danish-language ASR quality, identify gaps, and assess the feasibility of fine-tuning or model selection approaches

Design the integration points carefully — latency, error handling, data privacy — so voice becomes a first-class input channel

We are looking for someone who can say yes to

Must-have

2–4 years of production Python engineering experience, including async code, clean architecture patterns, and testable codebases

Direct experience with LLM orchestration frameworks (LangChain or similar) in a shipped product or serious project

Solid understanding of RAG systems: chunking strategies, embedding models, vector search, retrieval quality evaluation

Familiarity with vector databases — pgvector, Chroma, Weaviate, Pinecone, or equivalent

Comfortable owning a FastAPI service end-to-end: schema design, error handling, auth, containerization, deployment

Ability to reason about architectural trade-offs and communicate them clearly

Strong advantages

Hands-on experience designing or running local LLM inference — Ollama, vLLM, llama.cpp — in a real rather than toy context

Familiarity with knowledge graphs — ontology building, knowledge extraction, RAG integration

Experience with agentic frameworks: LangGraph, AutoGen, CrewAI, or custom tool-use / planning loops in production

Speech-to-text pipeline work — Whisper, Deepgram, Speechmatics, or comparable local STT — especially on non-English languages

Experience designing hybrid retrieval systems (dense + sparse, BM25 + vector) and re-ranking with cross-encoders

Familiarity with LLM observability and tracing tools (Arize Phoenix, LangSmith, or similar)

Exposure to multilingual NLP, particularly Danish or other Nordic languages

Nice to have

Knowledge of regulated-industry data handling, GDPR, or EU AI Act compliance considerations

Familiarity with cloud platforms (Azure preferred): managed services, container registries, CI/CD

Interested?

Send your application via our online form or directly to us.

Or send to karriere@microtech.dk · Call us at +45 7585 9444 for questions

We offer

• Beautiful offices at Viby J. station
• Free parking

• Opportunity to work hybrid
• Competitive salary

• Short decision-making process
• Personal development