Lead AI Engineer

ROLE SUMMARY

As a Lead Integration Engineer, you will lead the design, implementation, and operationalization of enterprise integration solutions that connect product platforms, AI-enabled applications, workflow systems, APIs, business systems, and external services. This role is critical to enabling seamless interaction between modern digital products and core enterprise systems, especially in environments where GenAI, agentic AI, workflow automation, and enterprise applications must work together reliably.

You will define and guide best practices for API design, event-driven architectures, service orchestration, integration lifecycle management, versioning, security, observability, and supportability. The role also requires strong understanding of emerging AI integration patterns such as tool calling, agent-to-agent (A2A) interactions, and Model Context Protocol (MCP)-aligned context exchange, as well as practical experience integrating with enterprise systems such as SAP and ServiceNow.

This role is ideal for a hands-on technical leader who combines deep integration engineering experience with strong system-thinking, enterprise awareness, and a product-oriented mindset.

KEY RESPONSIBILITIES

• Lead the design and implementation of secure, scalable, and maintainable integration architectures across APIs, event streams, enterprise systems, workflow platforms, and AI-enabled applications
• Define integration patterns and standards for REST APIs, asynchronous messaging, service orchestration, event-driven workflows, schema management, and lifecycle governance
• Design and support integrations that enable GenAI and agentic AI systems to interact reliably with downstream systems, tools, workflows, and data services
• Implement and guide patterns for agent-to-agent (A2A) interactions, tool-invocation integrations, and MCP-aligned context exchange mechanisms
• Lead integration work involving enterprise platforms such as SAP, ServiceNow, API management layers, workflow engines, event buses, and business process systems
• Drive API versioning, authentication, authorization, resiliency, observability, and backward compatibility practices across the integration landscape
• Collaborate with Techno-Functional Solution Architects, Solution Architects, Lead AI Engineers, Team Leads, and product stakeholders to convert use cases into implementable interface and integration designs
• Ensure integrations are observable, testable, supportable, and operationally mature, with appropriate monitoring, diagnostics, release validation, and incident handling practices
• Support decomposition of complex solution flows into technical stories, interface contracts, integration logic, error handling behavior, and support expectations
• Guide build and release practices for integration components, including automated testing, CI/CD, environment management, and operational controls
• Mentor integration engineers and application engineers on API design, eventing patterns, integration testing, system dependency management, and enterprise reliability expectations
• Contribute reusable artifacts such as API standards, schema templates, integration accelerators, error-handling patterns, and shared engineering guidelines

Required Qualifications

• 6 to 8+ years of experience in integration engineering, middleware engineering, API engineering, enterprise platform engineering, or related technical roles
• Proven experience designing and operating enterprise-grade APIs, integrations, event-driven architectures, service orchestration patterns, and system-to-system workflows
• Strong hands-on experience with Azure API Management, Azure Logic Apps, Azure Functions, Azure Service Bus, Event Grid, or equivalent integration and middleware platforms such as MuleSoft, Boomi, Kafka, RabbitMQ, Apigee, Kong, AWS API Gateway
• Strong expertise in REST APIs, JSON, OAuth2, OpenID Connect, webhook patterns, schema management, asynchronous messaging, event-driven communication, and API versioning / backward compatibility
• Practical experience integrating with enterprise systems such as SAP, ServiceNow, ERP platforms, ITSM systems, workflow platforms, and other downstream business applications
• Strong understanding of agentic AI integration patterns, including tool invocation, workflow coordination, context-sensitive system interactions, and distributed communication approaches such as Model Context Protocol (MCP) and agent-to-agent (A2A) interaction patterns
• Strong understanding of integration lifecycle management, including interface testing, release controls, failure handling, observability, supportability, dependency tracing, and long-term maintainability
• Experience implementing and supporting CI/CD, automated testing, deployment automation, API validation, and release-readiness controls for integrations and service interfaces
• Familiarity with observability and operational tooling such as Application Insights, Azure Monitor, OpenTelemetry, Datadog, AppDynamics, or equivalent monitoring and trace-analysis platforms
• Ability to collaborate across product, process, engineering, architecture, and platform teams to define practical, scalable, and supportable integration solutions
• Strong understanding of SDLC and build-own-operate expectations, including production support, incident response, root-cause analysis, and continuous improvement for long-lived APIs and integration assets
• Strong communication and stakeholder management skills, including the ability to simplify dependency, interface, and architecture trade-offs for both technical and non-technical stakeholders

Preferred Qualifications

• Experience implementing integrations that support GenAI, agentic AI, tool-calling, retrieval workflows, or AI-driven automation
• Exposure to Model Context Protocol (MCP), agent-to-agent (A2A) interaction models, and AI-aware integration patterns
• Familiarity with Azure OpenAI, Azure AI Studio, Semantic Kernel, LangChain, or equivalent AI platforms from an integration and orchestration standpoint
• Experience with SAP BTP, enterprise workflow orchestration, service virtualization, or API governance at scale
• Experience contributing reusable API accelerators, integration templates, contract standards, testing harnesses, or internal engineering frameworks
• Familiarity with performance tuning, dependency tracing, failure injection, idempotency patterns, and reliability engineering for distributed integrations
• Experience working in a build-own-operate product organization where APIs and integrations are treated as long-lived products rather than project-specific connectors
• Ability to influence architectural patterns and enterprise integration standards across multiple teams while remaining hands-on
• Familiarity with event-driven business process automation, workflow platforms, and integration support for order-to-cash, finance, service, or enterprise operations scenario.