Agentic & MCP Architect (Principal / Expert)

Our client is an international FinTech & Telecom group building a world-class AI capability from the ground up. The project involves creating autonomous and semi-autonomous agentic systems and intelligent platforms to transform and automate financial services for millions of users.

• Minimum 8–10 years of experience in software or machine learning engineering, including at least 3 years in a Technical Design Authority or Lead Engineering role.
• Proven hands-on track record of designing and deploying agentic or workflow automation systems running at scale in production.
• Deep practical knowledge of large language models (LLMs), agent frameworks, tool/function calling, context protocols (MCP), planning, and memory design.
• Experience integrating automated AI systems with core transactional platforms and enterprise applications.
• Experience designing permissioning, guardrails, and human oversight for systems taking action in regulated environments.

Nice to have:

• Experience in FinTech, banking, or other high-volume transactional environments.
• Recognized cloud, security, or AI engineering certifications.
• Postgraduate qualification (Master's or Ph.D.) in a technical discipline (Computer Science, Data Science, Mathematics, or a related field).

• Agentic Architecture: Design advanced agentic systems including planning, memory structures, orchestration mechanisms, and multi-agent design patterns.
• Tool & Context Integration Layer: Design and build Model Context Protocol (MCP) servers and connectors enabling agents to interact safely with enterprise systems.
• Execution Patterns & Runtime: Develop reusable execution patterns, agent templates, and the agent runtime environment.
• Safe Action Design: Design permissioning frameworks, human-in-the-loop oversight, escalation mechanisms, and automated rollbacks for agent-initiated actions.
• Evaluation & Quality: Design agent evaluation frameworks and monitor behavioral quality and safety in production.