Agentic AI Architect

Location: Bulgaria; Poland; Romania

Department: Delivery

Xebia is a global AI-first, digital transformation, and engineering partner. With over 25 years of experience and a team of 5,000 professionals across 16 countries, we help organizations design and build scalable products, platforms, and data-driven solutions. 

We specialize in Artificial Intelligence, Data and Cloud, Intelligent Automation, and Digital Products, combining deep technical expertise with a strong focus on engineering excellence and a people-first culture.  

In the CEE region, we’re a team of nearly 1,000 experts delivering modern applications, data platforms, and AI solutions for clients such as Millennium, ING, Play, Edenred, Arabian Drilling, FedEx, Leroy Merlin, Truecaller, Volotea, Schmitz Cargobull, and many, many more. We work with leading technologies including AWS, Azure, GCP, Databricks, and Snowflake, and combine strong engineering culture with a consulting mindset and a continuous focus on growth and knowledge sharing. 

 

You will be:
• defining the target architecture for an enterprise agentic AI foundation, separating shared capabilities from those specific to data management and data delivery use cases,
• assessing existing AI initiatives, components and platforms for maturity, business value, reuse potential, scalability, cost and control impact, and recommending what to reuse, adapt, buy, build or retire,
• benchmarking the client's approach against mature internal agentic patterns and current market practice,
• evaluating architecture and platform options across agent orchestration, APIs and MCP, data access and grounding, evaluation, observability and AgentOps/LLMOps,
• building non-functional requirements into the design from the start: security, privacy, resilience, performance, auditability, explainability, access control, human oversight and cost,
• preparing objective buy-versus-build recommendations for key components, covering total cost, speed, skills and vendor lock-in,
• shaping a lightweight lifecycle that takes team-level Copilot experiments from intake and assessment through assurance and promoaion to reusable, industrialized capabilities,
• building the proof of concept hands-on: agents, integrations, evaluation pipelines, tests and NFR evidence on representative workloads, with a clear plan for scale,
• working with data, technology, AI risk and business stakeholders in weekly reviews, demos and decision sessions,
• transferring knowledge throughout the engagement through pairing, architecture and code walkthroughs, runbooks and decision records, so client teams can continue independently.

Your profile:
• 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 via APIs and MCP, and retrieval and grounding on enterprise data,
• experience with evaluation, observability and lifecycle management of AI systems (AgentOps/LLMOps),
• a solid understanding of data management and data delivery, such as 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 track record of turning prototypes into reusable, controlled and supportable capabilities,
• the 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 ability to turn analysis into decision-ready recommendations,
• very good English, spoken and written.
Work from the European Union region and a work permit are required.

 

 

Recruitment Process:

CV review – HR call – Interview – Client Interview – Decision