The company is a long-established global firm in thermal management, mission-critical building systems, energy efficiency and decarbonization, with over 140 years in the field.
It helps customers use energy more efficiently and cut carbon emissions for sectors such as data centers, healthcare, pharmaceuticals, advanced manufacturing and higher education.
You would join the team building the company's Agentic AI Platform, a new system of AI agents that use tools, plan, reason and carry out multi-step business processes from start to finish.
Responsibilities
Lead the design and delivery of production multi-agent systems covering planning, tool and function calling, memory and orchestration, using frameworks such as LangGraph, AutoGen, CrewAI or Semantic Kernel.
Build complete RAG pipelines: document ingestion, chunking, embeddings, vector search (Azure AI Search, FAISS or pgvector), re-ranking and grounding agents in knowledge.
Connect agents to enterprise systems and APIs through tool calling and Model Context Protocol (MCP) or similar connector patterns.
Create and maintain evaluation frameworks for agent workflows, covering task completion, hallucination detection, trajectory analysis, LLM-as-judge pipelines and A/B tests.
Put safeguards in place for agents: prompt-injection defense, content filtering, role-based tool permissions, human review checkpoints and audit logs.
Fine-tune and tune LLMs where needed (LoRA/PEFT, prompt optimization, model routing, balancing latency and cost) on Azure OpenAI and Azure AI Foundry.
Build and assess classical ML models for classification, regression, forecasting and NLP where they support agent workflows.
Run LLMOps and MLOps for the platform: experiment tracking, prompt versioning, CI/CD, tracing and monitoring with LangSmith, Azure Monitor or OpenTelemetry, drift monitoring and retraining.
Work with data engineers on data quality, availability and governance across Azure Data Lake, Databricks and Synapse Analytics.
Turn unclear business problems into agentic AI solutions and present architecture choices and results to senior stakeholders.
Mentor junior data scientists, lead code and design reviews, and set engineering standards.
Requirements
Professional experience in data science or ML, including LLM or GenAI applications running in production.
Hands-on use of LangChain or LangGraph for agents.
Solid grasp of LLM application patterns, including prompt engineering.
Expert Python: pandas, NumPy, scikit-learn, async programming and FastAPI API development.
Experience with vector databases and embeddings, such as Azure AI Search, Pinecone, Weaviate, Qdrant, FAISS or pgvector.
Strong SQL and experience with large data volumes.
Conditions
Hybrid working with flexible hours and home office days.
Basic monthly salary of €2,700 to €4,215 at the start, with the final offer based on your experience, skills and qualifications.
A 13th-month salary is paid after your first 6 months.
Pay practices are fair, equitable and gender-neutral.
Benefits
Competitive salary and performance incentives.
Chance to design a new agentic AI platform from the ground up.
Azure and AI certification sponsorship and a continuous learning budget.
Technical leadership track and mentoring.
Access to current GenAI tools, compute and cross-domain AI projects.
Meal vouchers fully paid by the company.
Flexible benefits budget with more than 3,500 options, including a MultiSport card and medical and wellness services.
Retail and lifestyle discounts through Benefit+.
Allowance for private kindergarten or nursery.
Allowance for language courses, professional development and wellbeing support.
On-site perks: massages, fresh fruit, yoga, psychologist access, a health month, and events run by support groups, including volunteering and branding activities.
Seniority perks: an extra monthly allowance, medical care and support, and a wellbeing day.
Relocation support with a housing allowance if you move to Slovakia.