ml engineer for LLM applications

The role focuses on designing and building LLM applications and agentic workflows on Azure, including RAG pipelines, multi-agent orchestration, MCP tool integration, evaluation, guardrails, and cost control. It sets GenAI engineering standards for the account and is accountable for solution quality against agreed evaluation thresholds.

• Build LLM applications and agent workflows on Azure OpenAI using LangGraph, LangChain, or Semantic Kernel;
• Design RAG pipelines, including document ingestion, chunking, embeddings, vector search, hybrid retrieval, and re-ranking;
• Integrate enterprise tools and context through MCP servers and function or tool calling; design multi-agent systems;
• Engineer, version, and test prompts; run offline and online evaluations; fine-tune models where justified;
• Implement responsible-AI guardrails and LLM observability;
• Optimize token and inference costs through model routing, caching, and batching; report against cost budgets;
• Document prompts, evaluation results, and model choices; mentor engineers adopting GenAI patterns.

• Bachelor's degree in Computer Science, Engineering, Information Systems, a related field, or equivalent practical experience;
• 10+ Years in software or data engineering, including 3+ years in machine learning or NLP and 2+ years delivering production LLM applications on Azure OpenAI or equivalent;
• Expert Python skills and experience with LangGraph, LangChain, and/or Semantic Kernel;
• Experience with asynchronous, event-driven application design;
• Experience with Azure OpenAI, Azure AI Search, Azure AI Foundry / ML, Functions, Container Apps / AKS, Key Vault, and Application Insights;
• Knowledge of RAG design, including chunking, embeddings, vector databases, hybrid search, and re-ranking;
• Experience developing MCP servers or clients, function calling, multi-agent orchestration, and state management;
• Experience with LLM evaluation, fine-tuning, and model selection;
• Knowledge of guardrails, LLM observability, and FinOps for inference;
• English proficiency at C1 Advanced level;
• Nice to have: AWS Bedrock or GCP Vertex AI, semantic caching, model distillation, small-language-model deployment, Azure AI Engineer Associate (AI-102) or equivalent, experience in financial services or other regulated enterprise environments, experience with distributed teams.

• Relocation options are available for some positions;
• Annual holiday: 20 or 26 days, depending on overall seniority;
• Occasional leave: 1 or 2 days, depending on circumstances;
• Child care leave: 2 days or 16 hours per year;
• Absence due to force majeure: 2 days or 16 hours per year;
• Maternity leave: 20 weeks; parental leave: 41 weeks; paternity leave: 14 days;
• Access to expert-led technical courses, soft skills courses, in-house learning resources, external learning libraries, cloud programs, custom learning programs, technical mentorship, and leadership programs;
• Multisport card, wellbeing activities, preferential banking and car leasing offers, cafeteria discounts, and social benefit fund;
• Private healthcare insurance, dental support, travel insurance, optional family healthcare coverage, life insurance, and corrective glasses reimbursement;
• Social activities, online entertainment events, a multicultural team environment, project and account rotations, and new career opportunities;
• Benefits depend on the form of cooperation and apply to employees under an employment contract;
• Remote work is available only from Poland.