Objective

Work with the engineering team to implement, integrate, and validate agent-interoperability capabilities across the Marketing AI applications — enabling agents, services, and tools to communicate through shared, reusable patterns.

Key Responsibilities

- Define agent-to-agent (A2A) communication standards and integration patterns for the Marketing AI applications, and drive their adoption across teams.

- Ensure interoperability across internal and external agents — so in-house and third-party or partner agents can reliably discover, call, and work with one another.

- Develop reusable agent services and shared workflows that can be consumed by multiple AI applications.

- Implement Model Context Protocol (MCP) on Databricks and integrate MCP services with the existing agent ecosystem.

- Build connectors, APIs, orchestration workflows, and integration components required for agent communication.

- Integrate agents into end-to-end marketing workflows and business processes — embedding AI in how marketing actually runs, not just point-to-point connections.

- Execute end-to-end testing, performance testing, and interoperability validation for A2A and MCP scenarios.

- Establish testing, resiliency, and validation frameworks for multi-agent orchestrations — covering end-to-end, performance, failure and recovery, and interoperability scenarios.

- Work with internal engineering teams and third-party platform partners to test, troubleshoot, and validate integrations.

- Document reusable integration approaches and implementation patterns for future projects.

Expected Deliverables

- Operational A2A integrations across the Marketing AI applications.

- MCP-enabled services integrated with Databricks.

- Shared,



reusable agent workflows and integration components.

- Successful testing and validation of third-party platform integrations.

- Test reports, integration documentation, and production-ready implementation artifacts.

- A documented A2A communication standard and integration-pattern library, adopted across the AI applications.

- Validated interoperability across internal and external agents, and agents integrated into priority end-to-end marketing workflows.

- A resiliency and validation framework for multi-agent orchestrations.

Required Skills & Experience

- Robust software / integration engineering background (typically 10+ years) with production Python and REST API development.

- Hands-on experience building connectors, orchestration workflows, and reusable services.

- Familiarity with multi-agent / agent-interoperability patterns — agent-to-agent (A2A) communication, Model Context Protocol (MCP), and agent frameworks.

- Experience implementing services on Databricks.

- Experience integrating third-party SaaS / AI platforms via APIs.

- Rigorous approach to integration, performance, and end-to-end testing.

- Bachelor’s degree in Computer Science, Software Engineering, or a related field (or equivalent experience).

- Experience defining integration standards and multi-agent orchestration patterns (A2A, MCP, agent frameworks) at enterprise scale.

- Building resiliency and validation frameworks for distributed or multi-agent systems — failure modes, retries, and observability of agent interactions.

Nice to Have

- Experience with LLM / generative-AI applications, retrieval-augmented generation, and agentic architectures.

- Exposure to marketing or sales technology ecosystems.

📌 AI Integration Specialist (Bengaluru)
🏢 GLIDER.ai
📍 Bengaluru