Agentic & MCP Architect (Principal / Expert)

EmergeSoft; Polska; On-site; PLN 583,000 - 738,000; Full time

Job summary

EmergeSoft is building a world-class AI capability for a global FinTech & telecom group. We seek an Agentic & MCP Architect to lead hands-on architectural work across agent frameworks, MCP servers, and runtime design.

The role focuses on safe action design, memory orchestration, and scalable agent systems with strong emphasis on governance, security, and production-readiness.

Qualifications

• 8–10+ years in software or ML engineering with leadership exposure.
• At least 3 years in a Technical Design Authority or Lead role.
• Hands-on practice with agent frameworks, LLMs, and MCP standards.
• Experience integrating AI with core transactional platforms.
• Knowledge of safety, guardrails, and human oversight for autonomous systems.

Responsibilities

• Design advanced agentic architectures, memory, and orchestration patterns.
• Build MCP servers/connectors enabling safe enterprise interactions.
• Create reusable execution patterns and agent runtime components.
• Implement safe action design with permissions and rollbacks.
• Establish evaluation frameworks to monitor behavior and safety.

Skills

8–10+ years software/ML engineering

3+ years in Technical Design Authority

LLMs and agent frameworks

MCP and context protocols

Enterprise integration

Tools

Model Context Protocol (MCP)

Job description

We are building a world-class AI capability (AI Squad) from the ground up for an international FinTech & Telecom group. Our mission is to create autonomous and semi-autonomous agentic systems and intelligent platforms that will transform and automate financial services for millions of users worldwide.

We are seeking an Agentic & MCP Architect to serve as the chief Design Authority for agentic systems across Group FinTech. This is a hands-on architecture role within a build team — ranging from designing agent frameworks and tool servers to defining Model Context Protocol (MCP) standards, context integration layers, and predictable execution in production.

• 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 core agent runtime environment.
• Safe Action Design: Design permissioning frameworks, human-in-the-loop oversight, escalation paths, and automated rollbacks for agent-initiated actions.
• Evaluation & Quality: Establish agent evaluation frameworks and monitor behavioral quality and safety in production environments.

About the Role & Mission

We are building a world-class AI capability (AI Squad) from the ground up for an international FinTech & Telecom group. Our mission is to create autonomous and semi-autonomous agentic systems and intelligent platforms that will transform and automate financial services for millions of users worldwide.

We are seeking an Agentic & MCP Architect to serve as the chief Design Authority for agentic systems across Group FinTech. This is a hands-on architecture role within a build team — ranging from designing agent frameworks and tool servers to defining Model Context Protocol (MCP) standards, context integration layers, and predictable execution in production.

What You’ll Do

• 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 core agent runtime environment.
• Safe Action Design: Design permissioning frameworks, human-in-the-loop oversight, escalation paths, and automated rollbacks for agent-initiated actions.
• Evaluation & Quality: Establish agent evaluation frameworks and monitor behavioral quality and safety in production environments.

What We’re Looking For

• Experience: 8–10+ years in software or machine learning engineering, including at least 3 years in a Technical Design Authority or Lead Engineering role.
• Production Agentic Practice: Proven hands-on track record of designing and deploying agentic or workflow automation systems running at scale in production.
• Domain Expertise: Deep practical knowledge of Large Language Models (LLMs), agent frameworks, tool/function calling, context protocols (MCP), planning, and memory design.
• Enterprise Integration: Experience integrating automated AI systems with core transactional platforms and enterprise applications.
• Guardrails & Security: Experience designing permissioning, guardrails, and human oversight for systems taking autonomous action in regulated environments.

Nice-to-Haves

• Background in FinTech, banking, or 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 related field).

Why Join Us?

• Bleeding-Edge Innovation: Lead the enterprise implementation of Model Context Protocol (MCP) and multi-agent orchestration patterns from day one.
• True Authority: Set the architectural standards, execution patterns, and technical direction for the entire AI capability.

#AgenticAI #MCP #AIArchitecture #LLM #MultiAgent #GenAI #FinTech #AIArchitect #Hiring #JobOpportunity #TechJobs