{"id":4609184,"url":"https://alion.io/job/microtech-software-experienced-ai-engineer-2","title":"Experienced AI Engineer","company":{"id":4404723,"name":"MicroTech Software","domain":"microtech.dk","url":"https://alion.io/company/microtech-software","size_band":null,"is_staffing_agency":false,"employer_type":"services","is_intermediary":false,"listed_via":null,"ats_vendor":null,"truth_index":null},"role":"AI/ML","role_family":"AI/ML","seniority":null,"employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Aarhus, Denmark"],"countries":["DK"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":true,"has_equity":false,"technologies":[{"name":"Agentic Workflows","optional":false},{"name":"AI Agents","optional":false},{"name":"Chroma","optional":false},{"name":"Clean Architecture","optional":false},{"name":"FastAPI","optional":false},{"name":"Fine-tuning","optional":false},{"name":"GraphRAG","optional":false},{"name":"Knowledge Graph","optional":false},{"name":"LangChain","optional":false},{"name":"LangGraph","optional":false},{"name":"llama.cpp","optional":false},{"name":"LLM","optional":false},{"name":"Ollama","optional":false},{"name":"pgvector","optional":false},{"name":"Pinecone","optional":false},{"name":"Python","optional":false},{"name":"RAG","optional":false},{"name":"Speech Recognition","optional":false},{"name":"vLLM","optional":false},{"name":"Weaviate","optional":false},{"name":"Arize Phoenix","optional":true},{"name":"AutoGen","optional":true},{"name":"Azure","optional":true},{"name":"CI/CD","optional":true},{"name":"CrewAI","optional":true},{"name":"Deepgram","optional":true},{"name":"EU AI Act","optional":true},{"name":"GDPR","optional":true},{"name":"LangSmith","optional":true},{"name":"NLP","optional":true},{"name":"PostgreSQL","optional":true},{"name":"Whisper","optional":true}],"status":"live","first_seen_at":"2026-11-18T23:00:00Z","employer_posted_date":null,"last_verified_at":"2026-11-18T23:00:00Z","board_verified":false,"closed_at":null,"days_open":0,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":0},"description":"About MicroTech Software\n\nMicroTech is a small software company with more than 35 years of experience building custom solutions in close dialogue with our customers, mainly in banking and insurance. Since 2025, applying AI has been a major focus for us.\n\nWe value quality over quantity, and we keep the customer experience at the centre. Expect great colleagues and a busy but relaxed workday in an informal atmosphere. We also care about ESG and like to give back, for example through sponsorships and by being an inclusive workplace that welcomes employees who need special accommodations.\n\nAbout the role\n\nYou’ll help shape the architecture of a live AI product running on our own on-prem LLM stack.\n\nTwo big projects are coming up, and you’ll play a key part in both:\n\nVoice-to-workflow: making speech a first-class input channel in our agentic workflows\n\nMoving to a graph architecture: going from RAG to GraphRAG by building a knowledge graph and integrating it into our existing pipeline\n\nResponsibilities\n\nShape the architecture of a live AI product\n\nEvaluate and challenge design decisions across the stack, including retrieval strategies, LLM backend selection, service boundaries and data flow, and propose improvements with clear reasoning\n\nTake part in technical planning with the team and with insurance-domain stakeholders, turning vague requirements into concrete engineering tasks\n\nIdentify technical debt, assess its cost and make the case for addressing it\n\nDevelop and optimize our on-prem AI stack\n\nFurther develop and optimize our self-hosted LLM stack: local models, local embedding and on-prem vector stores\n\nEvaluate open-weight LLMs for Danish-language RAG quality, weighing latency, accuracy and hardware requirements\n\nMove to a graph architecture (RAG → GraphRAG)\n\nHelp design and build a knowledge graph for our domain, including ontology and knowledge extraction\n\nIntegrate the knowledge graph into our existing RAG pipeline and measure the effect on retrieval quality\n\nDesign and build agentic workflows\n\nDesign multi-step agent architectures using LangGraph or equivalent frameworks that can route, plan, use tools and synthesize across document corpora\n\nDefine tool-use interfaces, memory patterns and failure-handling strategies for agent loops running in production\n\nWork with domain experts to identify automation opportunities worth building\n\nEnable voice-to-workflow capabilities\n\nHelp design a pipeline that integrates local speech-to-text models into agentic workflows\n\nEvaluate Danish-language ASR quality, identify gaps and assess whether fine-tuning or model selection is the better approach\n\nDesign the integration points carefully, with attention to latency, error handling and data privacy, so voice becomes a first-class input channel\n\nRequirements\n\n2–4 years of production Python engineering experience, including async code, clean architecture patterns and testable codebases\n\nDirect experience with LLM orchestration frameworks (LangChain or similar) in a shipped product or serious project\n\nSolid understanding of RAG systems: chunking strategies, embedding models, vector search and retrieval quality evaluation\n\nFamiliarity with vector databases such as pgvector, Chroma, Weaviate or Pinecone\n\nComfortable owning a FastAPI service end-to-end: schema design, error handling, auth,\n\ncontainerization and deployment\n\nAbility to reason about architectural trade-offs and communicate them clearly\n\nHands-on experience designing or running local LLM inference (Ollama, vLLM, llama.cpp) in a real rather than toy context\n\nNice to have\n\nFamiliarity with knowledge graphs, including ontology building, knowledge extraction and RAG integration (especially relevant)\n\nSpeech-to-text pipeline work (Whisper, Deepgram, Speechmatics or comparable local STT), especially on non-English languages (especially relevant)\n\nExperience with agentic frameworks (LangGraph, AutoGen, CrewAI) or custom tool-use and planning loops in production\n\nHybrid retrieval systems (dense + sparse, BM25 + vector) and re-ranking with cross-encoders\n\nLLM observability and tracing tools (Arize Phoenix, LangSmith or similar)\n\nMultilingual NLP, particularly Danish or other Nordic languages\n\nKnowledge of regulated-industry data handling, GDPR or EU AI Act compliance\n\nCloud platforms (e.g. Azure), container registries and CI/CD\n\nWhat we offer\n\nBeautiful offices: art on the walls, plenty of green plants and high ceilings\n\nGreat location: bus, train and light rail right outside the door, easy to reach by car, and free parking\n\nFlexible work: a hybrid setup with the option to work from home up to around 2 days a week after the initial onboarding\n\nSmall organisation: very short decision-making processes and great opportunities for co-responsibility\n\nPersonal development: varied tasks, direct client contact and support for further education\n\nAll phases: you’ll work on everything from definition and solution design to programming and production\n\nCompetitive salary: an attractive compensation package that matches your skills\n\nPlease note\n\nStart date: as soon as possible. We’ll still take the time to find the right person, so we review applications on an ongoing basis and will keep the position open until it’s filled.\n\nThis is a hybrid role based at our office in Viby J., Aarhus. It is not a remote position.\n\nWe cannot offer work permit sponsorship or relocation support. Applicants must already have the right to work in Denmark.","description_format":"text","description_chars":5459,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":["Flexible schedule"],"hiring_locations":[{"name":"Denmark","iso":"DK","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Custom Software Development","InsurTech"],"lifecycle":[{"event":"open","at":"2026-11-19T14:52:30Z"}],"visa":[],"liveness":{"score":86,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.86,"p_room":1,"age_days":0,"expected_fill_days":26,"reasons":["seen:0","win:early"],"computed_at":"2026-11-19T19:19:41Z"},"pay":null,"html_url":"https://alion.io/job/microtech-software-experienced-ai-engineer-2","json_url":"https://alion.io/job/microtech-software-experienced-ai-engineer-2.json","meta":{"generated_at":"2026-11-19T19:19:41Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":1570,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-20T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.1,"usd":0.01,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":4404723},"rest":"https://alion.io/mcp/rest/get_company?id=4404723"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fmicrotech-software-experienced-ai-engineer-2"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"free","price":{"credits":0,"usd":0},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Fmicrotech-software-experienced-ai-engineer-2"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.1,"usd":0.01},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Fmicrotech-software-experienced-ai-engineer-2"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/microtech-software-experienced-ai-engineer-2\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fmicrotech-software-experienced-ai-engineer-2"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":4609184}},{"tool":"search_jobs","arguments":{"company":"microtech.dk","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":4609184},"note":"people open to offers who fit this vacancy"}],"note":"The same data through MCP tools: https://alion.io/mcp/open needs no sign-in (compact searches, postings, people); https://alion.io/mcp with an Alion account has everything. Docs: https://alion.io/developers"}}