Senior Data Scientist (Agentic AI Platform)

About the role

A Senior Data Scientist is sought to build an Agentic AI Platform: a system of autonomous, tool-using AI agents that plan, reason and execute complex business workflows end-to-end. The role combines strong ML fundamentals with hands-on LLM application development, agent orchestration and Microsoft Azure, and includes mentoring junior team members and setting technical direction for GenAI initiatives.

Key responsibilities

• Design, build and productionise multi-agent systems (planning, tool/function calling, memory, orchestration) with frameworks such as LangGraph, AutoGen, CrewAI or Semantic Kernel.
• Build end-to-end RAG pipelines: ingestion, chunking, embeddings, vector search (Azure AI Search, FAISS, pgvector), re-ranking and grounding.
• Integrate agents with enterprise systems and APIs via tool/function calling and Model Context Protocol (MCP).
• Build and maintain LLM evaluation frameworks, guardrails, safety and governance (prompt-injection defence, content filtering, human-in-the-loop checkpoints, audit logging).
• Fine-tune and optimise LLMs (LoRA/PEFT, prompt optimisation, model routing) on Azure OpenAI / Azure AI Foundry, and design, build and evaluate classical ML models.
• Own LLMOps/MLOps: experiment tracking, prompt versioning, CI/CD, observability and tracing (LangSmith, Azure Monitor, OpenTelemetry), drift monitoring and retraining.
• Collaborate with data engineers on data quality and governance across Azure Data Lake, Databricks and Synapse, and mentor junior data scientists.

Required profile

• Professional experience in data science / ML, with LLM or GenAI applications in production.
• Hands-on experience with agentic frameworks (LangChain or LangGraph) and classical ML.
• Bachelor's or Master's degree in a related field preferred.
• Preferred: Microsoft certifications AI-102 and DP-100, experience fine-tuning open-source LLMs (Llama, Mistral, Phi) with LoRA/QLoRA, and big data experience with Apache Spark (PySpark) via Databricks.

Required skills

• Expert-level Python (pandas, NumPy, scikit-learn, FastAPI, async programming)
• Vector databases and embeddings (Azure AI Search, Pinecone, Weaviate, Qdrant, FAISS, pgvector)
• Strong SQL and Azure services (OpenAI, AI Foundry, Azure ML, AI Search, Databricks, Data Factory, Synapse)
• Preferred: MCP, LangSmith, Langfuse, Arize Phoenix, Docker, Kubernetes (AKS), Azure Container Apps, knowledge graphs and graph RAG

What we offer

• Initial basic salary of 1,010,233 to 1,578,483 HUF per month, depending on experience and skills.
• Meal vouchers, flexible benefits budget, retail discounts, private kindergarten/nursery allowance, flexible hours and home office days.
• On-site benefits and relocation support with housing allowance if moving to Slovakia.