Job Summary

The Agentic Integration Architect connects enterprise systems, data, and AI. The role designs API, event-driven, messaging, cloud, and hybrid integration architectures, and builds MCP, AI Gateway, AI agent, and LLM-enabled integration solutions on top of them. It brings deep hands-on expertise in one or two integration platforms (MuleSoft, Kong, Boomi, Azure Integration Services, Kafka, or Workato), with working knowledge across the wider integration landscape.

As a CoE role, it defines reference architectures, frameworks, accelerators, governance, and best practices, evaluates emerging technology through PoCs, shapes integration strategy, creates architecture and thought-leadership assets, and mentors teams. It also supports Solutions and Advisory teams with expert input to workshops and proposals.

Design API, event-driven, messaging, cloud and hybrid integration architectures; build MCP, AI Gateway, AI Agent and LLM-enabled integration solutions; deep hands-on expertise in one or two of MuleSoft, Kong, Boomi, Azure Integration Services, Kafka or Workato, with working knowledge across the broader integration landscape; define reference architectures, frameworks, accelerators, governance and best practices; evaluate emerging technology and build PoCs; shape integration strategy; create architecture and thought-leadership assets; mentor teams and support workshops and proposals. Mandatory across all roles: practical AI-native engineering; strong modern application development; cloud-native, API, microservices and DevSecOps grounding; hands-on experience with at least one agent harness such as Claude Code, GitHub Copilot, Codex, Kiro or Cursor; enterprise security, governance, evaluation, observability and cost awareness.

Key Responsibilities

A. Integration Architecture

• Design API, event-driven, messaging, cloud, and hybrid integration architectures (on-premises, multi-cloud, SaaS, and legacy).
• Define API strategy and lifecycle: design-first, versioning, contracts, catalogs, discoverability, and API products.
• Design event and messaging architectures: topics, schemas and schema evolution, ordering, delivery guarantees, idempotency, replay, dead-letter handling, and event governance.
• Apply integration patterns (orchestration vs. choreography, saga, CQRS, outbox, strangler, canonical models) with appropriate resilience and error handling.

B. AI-Enabled Integration

• Build MCP servers and gateways that expose enterprise APIs, events, and data to AI agents safely and consistently.
• Design AI Gateway capabilities: model routing and failover, authentication and quotas, rate limiting, token and cost controls, caching, prompt and response policies, guardrails, and audit logging.
• Build AI agent and LLM-enabled integration solutions, such as intelligent mapping and transformation, document and message classification, event enrichment, and agent-driven orchestration across systems.
• Design agent-to-system integration patterns: tool contracts, idempotency, scoped credentials, approval gates, and safe retries.

C. Platform Expertise

• Provide deep, hands-on architecture and build leadership on one or two of MuleSoft, Kong, Boomi, Azure Integration Services, Kafka, or Workato.
• Maintain working knowledge across the broader landscape (API gateways and management, iPaaS, ESB/legacy middleware, streaming platforms, service mesh, cloud-native integration services, B2B/EDI) and guide platform selection and coexistence.
• Architect hybrid connectivity, networking, and security (private links, VPN, zero-trust, API security) for integration workloads.

D. Reference Architectures, Governance & Accelerators

• Define reference architectures, frameworks, and accelerators: API and event templates, MCP server and gateway templates, AI gateway policy packs, connector libraries, and CI/CD pipelines for integration assets.
• Establish governance and best practices: API and event standards, schema and contract governance, lifecycle management, security policies, and an integration operating model.
• Define evaluation, observability, security, and cost controls for integrations and AI-enabled flows (contract testing, tracing, SLOs, least privilege, token and platform cost management).

E. Innovation & Proofs of Concept

• Evaluate emerging technology (MCP and agent interoperability protocols, AI gateways, platform AI features, streaming and event standards) and recommend where it fits.
• Build PoCs that prove feasibility and value; convert successful PoCs into reusable assets and delivery-ready patterns.
• Use AI-native engineering and agent harnesses to build and iterate quickly while maintaining production quality.

F. Integration Strategy & Engagement Support

• Shape integration strategy: target architecture, platform rationalization, API and event maturity roadmaps, and AI-readiness of the integration layer.
• Provide expert architecture input to customer roadmaps, workshops, and demos led by Solutions and Advisory teams.
• Contribute architecture content, estimation inputs, and risk framing to proposals and pursuits.
• Turn field feedback and engagement learnings back into CoE frameworks and accelerators.

G. Thought Leadership & Mentoring

• Create architecture and thought-leadership assets: whitepapers, point-of-view documents, reference diagrams, blogs, and briefing material.
• Mentor engineers and architects; build capability across integration platforms and AI-enabled integration; contribute to training and certification pathways.

Skill Requirements

• Bachelor's or Master's degree in Computer Science, Engineering, Information Systems, or an equivalent field, or equivalent practical experience.
• 12+ years in software or integration architecture, with at least 6 years on one or more of the named integration platforms and at least 2 years building LLM-based, agent, or AI-enabled integration solutions.
• Track record of delivering enterprise-scale API, event-driven, or hybrid integration programs, and of supporting field teams in customer workshops or proposals.

Technical Skills (Must Have)

1. API architecture: REST, GraphQL, gRPC, AsyncAPI/OpenAPI, API lifecycle management, security (OAuth2/OIDC, mTLS), and API product thinking.
2. Event-driven and messaging architecture: Kafka and other brokers, schema registries, delivery semantics, stream processing basics, event modeling and governance.
3. Integration patterns and hybrid architecture: orchestration vs. choreography, saga, outbox, CQRS, legacy modernization, hybrid and multi-cloud connectivity.
4. Integration platform depth: deep hands-on expertise in one or two of MuleSoft, Kong, Boomi, Azure Integration Services, Kafka, or Workato, including design, build, deployment, and governance.
5. Broader integration landscape: working knowledge of other API gateways, iPaaS, middleware, streaming, service mesh, and B2B platforms, and when to use each.
6. MCP and AI Gateway: designing and building MCP servers; AI gateway policy, routing, quotas, guardrails, and observability.
7. AI agent and LLM-enabled integration: agent architecture, tool contracts, orchestration, prompt and context engineering, structured outputs, LLM-assisted transformation and classification.
8. AI-native engineering: practical use of AI across the development lifecycle; hands-on with at least one agent harness (Claude Code, GitHub Copilot, Codex, Kiro, or Cursor).
9. Modern application development: strong proficiency in at least one language such as Java, Python, TypeScript, or Go; clean architecture, testing, code review.
10. Cloud-native, API & microservices: AWS/Azure/GCP, containers, Kubernetes, serverless, service design, resilience patterns.
11. DevSecOps: CI/CD for integration assets, infrastructure as code, secrets and certificate management, secure SDLC, API security testing.
12. Enterprise readiness: security, governance, evaluation, observability, and cost awareness, including token, throughput, and platform licence cost modeling.

Behavioral & Professional Skills

• Translates integration complexity into clear target architectures and reusable patterns.
• Clear communication with architects, engineers, and business stakeholders; strong written and visual architecture communication.
• Pragmatic about platform choice; avoids favouring a vendor by default.
• Mentoring, collaboration, and a strong sense of ownership across Advisory, Solutions, and CoE teams.

Other Requirements

Role-specific

• Service mesh and API platform engineering (Istio, Envoy, Kong Mesh, Gateway API).
• Change data capture and data integration (Debezium, Fivetran, Informatica, Airbyte) and data-in-motion architectures.
• Agent interoperability protocols (A2A) and agent registries; agent frameworks (LangGraph, Claude Agent SDK, OpenAI Agents SDK, Semantic Kernel).
• AI gateway and LLM proxy tooling (e.g., Kong AI Gateway, Azure API Management AI features, LiteLLM, Portkey).
• Platform-native AI features (e.g., MuleSoft AI Chain / Agentforce integration, Boomi AI, Workato AI, Azure AI Foundry integration).
• Event governance tools and API management portals (Confluent Schema Registry, AsyncAPI tooling, Backstage).
• B2B/EDI, healthcare (HL7/FHIR) or financial messaging standards (ISO 20022, SWIFT).
• Performance and load testing; chaos engineering for integration platforms.
• Domain exposure in BFSI, healthcare, telecom, retail, manufacturing, or public sector.

Common competencies (mandatory across all roles)

• Practical AI-native engineering and strong modern application development.
• Cloud-native, API, microservices, and DevSecOps grounding.
• Hands-on experience with at least one agent harness (Claude Code, GitHub Copilot, Codex, Kiro, Cursor).
• Enterprise security, governance, evaluation, observability, and cost awareness.

Certifications (preferred, not mandatory)

• Platform certifications: MuleSoft (Integration Architect), Boomi (Architect), Kong (Gateway/Konnect), Azure (AZ-204, AZ-305, Integration Services), Confluent/Kafka (CCDAK, CCAAK), Workato (Automation Pro/Architect).
• Cloud solution architect certifications (AWS, Azure, or GCP).
• TOGAF or equivalent architecture certification.