Agentic AI Architect

Description

The company is a global partner for AI, digital transformation and engineering, with more than 25 years of experience, about 5,000 staff and presence in 16 countries. It helps organisations design and build scalable products, platforms and data-driven solutions.

Work areas include artificial intelligence, data and cloud, intelligent automation and digital products. The company combines deep technical skill with a focus on engineering quality and a people-first approach.

The CEE region has nearly 1,000 specialists building applications, data platforms and AI solutions on AWS, Azure, GCP, Databricks and Snowflake. The team blends an engineering culture with consulting work and shares knowledge and grows continuously.

Responsibilities

• Define the target architecture for an enterprise agentic AI foundation, keeping shared capabilities apart from those tied to data management and data delivery.
• Assess existing AI initiatives, components and platforms on maturity, business value, reuse potential, scalability, cost and control, then recommend whether to reuse, adapt, buy, build or retire each one.
• Compare the client's approach with mature internal agentic patterns and current market practice.
• Evaluate architecture and platform options for agent orchestration, APIs and MCP, data access and grounding, evaluation, observability and AgentOps/LLMOps.
• Design security, privacy, resilience, performance, auditability, explainability, access control, human oversight and cost into the architecture from the outset.
• Prepare objective buy-versus-build recommendations for key components, weighing total cost, speed, skills and vendor lock-in.
• Shape a lightweight lifecycle that moves team-level Copilot experiments from intake and assessment, through assurance and promotion, to reusable, industrialised capabilities.
• Build the proof of concept yourself, including agents, integrations, evaluation pipelines, tests and non-functional evidence on representative workloads, with a clear plan for scaling.
• Work with data, technology, AI risk and business stakeholders in weekly reviews, demos and decision sessions.
• Pass on knowledge through pairing, architecture and code walkthroughs, runbooks and decision records so the client's teams can carry on alone.

Requirements

• At least 7 years of professional experience in software, data or AI engineering, including recent work as a solution architect, AI architect or lead engineer.
• Hands-on experience designing and delivering LLM-based and agentic solutions beyond the prototype stage.
• Strong Python skills and practical experience with agent orchestration, tool integration through APIs and MCP, and retrieval and grounding on enterprise data.
• Experience with evaluation, observability and lifecycle management of AI systems (AgentOps/LLMOps).
• A solid grasp of data management and data delivery, including metadata, data quality, lineage, governance, pipelines and data products.
• Experience in regulated environments where security, privacy, auditability and AI risk requirements shape the architecture.
• A record of turning prototypes into reusable, controlled and supportable capabilities.
• Ability to assess commercial products against open-source and build options objectively, including total cost of ownership and lock-in.
• Confidence with senior technical and business stakeholders and the skill to turn analysis into recommendations that support decisions.
• Very good spoken and written English.

Conditions

You must be based in the European Union and hold a work permit.

Hiring steps: CV review, HR call, interview, client interview, then decision.