AI Architect (Agentic Process Automation)

We are seeking a hands-on AI Architect to design, govern, and scale enterprise-grade Agentic AI, Copilot, and Intelligent Automation solutions. The role combines AI architecture, enterprise data strategy, evaluation engineering, governance, and intelligent process automation to deliver secure, scalable, and business-driven AI solutions.

Key Responsibilities:

• Design and deliver enterprise-grade Agentic AI, Copilot, RAG, and Intelligent Automation solutions.
• Architect multi-agent systems including planning, reasoning, memory management, workflow orchestration, tool integration, and Human-in-the-Loop controls.
• Define enterprise AI strategy, reference architectures, standards, governance frameworks, best practices, and reusable accelerators.
• Lead AI platform decisions spanning foundation models, agent frameworks, enterprise data, orchestration platforms, and integration patterns.
• Architect and provide technical leadership for Python-based AI platforms, agent frameworks, automation services, APIs, and enterprise integrations.
• Ensure AI solutions meet enterprise requirements for scalability, reliability, observability, security, compliance, and operational excellence.
• Collaborate with product, engineering, security, data, and business stakeholders to identify high-value AI opportunities and deliver measurable business impact.
• Conduct architecture reviews, support Architecture Review Boards (ARB), and oversee delivery across multiple AI initiatives.

Enterprise Integration, Data & AI Quality Engineering:

• Integrate AI solutions with enterprise platforms including ERP, CRM, ITSM, HR, Finance, SharePoint, and other business systems.
• Design AI architectures leveraging Microsoft Fabric, Databricks, Snowflake, Azure Data Lake, Enterprise Data Platforms, and enterprise knowledge repositories.
• Architect secure integrations using APIs, Graph APIs, OAuth2, Function Calling, MCP, Agent-to-Agent communication, and event-driven architectures.
• Design enterprise knowledge architectures across structured, semi-structured, and unstructured data sources.
• Define data strategies covering knowledge sourcing, metadata management, chunking strategies, embedding architectures, vectorization, and retrieval optimization.
• Design scalable data processing pipelines, orchestration services, and AI workloads using Python and cloud-native technologies.
• Design and govern evaluation datasets, benchmark suites, golden test sets, and domain-specific validation frameworks.
• Establish methodologies for measuring accuracy, groundedness, relevance, reasoning quality, latency, cost efficiency, and business outcomes.
• Define evaluation pipelines for prompts, RAG systems, copilots, and autonomous agents using automated and human evaluation approaches.
• Partner with business, domain, and data teams to establish trusted AI-ready data foundations, feedback loops, and continuous improvement processes.

Governance, Security & Reliability:

• Implement Responsible AI practices covering privacy, security, compliance, auditability, risk management, ethical AI, and PII protection.
• Define observability, testing, hallucination detection, resiliency, disaster recovery, model monitoring, and operational support strategies.
• Establish AI quality gates, release criteria, evaluation standards, and governance processes for production AI systems.
• Drive token governance, model routing, semantic caching, cost optimization, and mitigation strategies for bias, drift, and reliability risks.

Foundation Models & GenAI:

• Provide technical leadership on LLM platforms including OpenAI GPT, Azure OpenAI, Anthropic Claude, Microsoft Copilot, and emerging foundation models.
• Apply advanced Prompt Engineering, Context Engineering, Knowledge Grounding, Function Calling, Agent Memory, and Model Routing techniques.
• Design and optimize Retrieval-Augmented Generation (RAG) solutions leveraging enterprise search, vector databases, embeddings, and knowledge management platforms.

Required Qualifications:

• Bachelor's or Master's degree in Computer Science, Engineering, Data Science, or a related discipline.
• 8+ years of software engineering experience, including a minimum of 3 years focused on AI/ML, Generative AI, Agentic AI, Copilot, or Intelligent Automation solutions.
• Strong expertise in Python, including development of AI agents, APIs, automation services, data processing pipelines, orchestration frameworks, and evaluation platforms.
• Hands-on experience building enterprise AI applications using technologies such as FastAPI, LangChain, LangGraph, , Pandas, or similar frameworks.
• Hands-on experience with AI development tools such as Cursor AI, GitHub Copilot, and Microsoft 365 Copilot.
• Extensive experience with LLM platforms including OpenAI, Azure OpenAI, Anthropic Claude, and similar technologies.
• Deep understanding of RAG, vector databases, embedding models, enterprise search, knowledge management architectures, and AI evaluation frameworks.
• Strong knowledge of Graph APIs, OAuth2, SSO, enterprise integration patterns, API design, microservices, Docker, Kubernetes, event-driven architecture, and CI/CD pipelines.
• Experience designing AI evaluation datasets, benchmark frameworks, quality gates, model performance metrics, and validation methodologies.
• Experience building AI business cases, value realization frameworks, ROI assessments, and executive-level presentations.

Preferred Qualifications:

• Experience leading enterprise-scale Agentic AI and multi-agent deployments.
• Knowledge of model fine-tuning, reinforcement learning, and model optimization techniques.
• Familiarity with Model Context Protocol , AI orchestration platforms, and agent communication protocols.
• Exposure to MLOps, LLMOps, prompt management, model monitoring, and AI compliance frameworks.

The potential base pay range for this role, when annualized, is 227 000,00 zł - 421 400,00 zł.