Agentic AI Engineer

20h•Hybrid

About The Position

The Agentic AI Engineer builds and supports production-grade agentic AI solutions using cloud-native AI platforms such as AWS Bedrock, Azure AI Foundry, or GCP Vertex AI. The role applies data engineering expertise to develop scalable APIs, data pipelines, integrations, agent tools, and AI-enabled applications. The engineer designs agents capable of planning, reasoning, tool use, workflow orchestration and automation, retrieval-augmented generation, memory management, multi-step task execution, and multi-agent collaboration. The role also develops secure, interoperable agent ecosystems using MCP and A2A patterns or protocols, and builds backend services and integrations that connect agents to enterprise applications, databases, documents, external systems, and data sources. The position involves implementing RAG solutions, evaluating and improving agent performance, troubleshooting agent and integration issues, and collaborating across architecture, product, backend, data engineering, and DevOps teams. Work follows best practices for testing, CI/CD, monitoring, documentation, and secure deployment.

Nice To Haves

GraphRAG experience.

Responsibilities

Build and support production-grade Agentic AI solutions using cloud-native platforms such as AWS Bedrock, Azure AI Foundry, or GCP Vertex AI.
Design intelligent agents with tool use, workflow orchestration, retrieval-augmented generation, reasoning, task automation, memory management, and multi-agent collaboration capabilities.
Create scalable APIs, data pipelines, integrations, agent tools, and AI-enabled applications using data engineering practices.
Design, develop, and maintain Agentic AI applications on AWS Bedrock, Azure AI Foundry, or GCP Vertex AI.
Build agents capable of planning, reasoning, tool calling, memory management, workflow automation, and multi-step task execution.
Implement MCP integrations so agents and LLM applications can securely connect to external tools, APIs, enterprise systems, databases, and data sources.
Apply A2A patterns or protocols for agent discovery, agent-to-agent communication, task delegation, and multi-agent collaboration.
Develop backend services, APIs, connectors, and integrations for agent access to enterprise applications, databases, documents, and external systems.
Implement RAG solutions using vector databases, embeddings, document processing, semantic search, and knowledge retrieval patterns.
Evaluate, test, and improve agent performance, including prompt quality, response accuracy, latency, reliability, guardrails, security, and cost efficiency.
Debug and resolve issues involving agent behavior, API integrations, tool execution, MCP servers or clients, A2A communication, data retrieval, workflow failures, model responses, and production deployments.
Collaborate with architects, product owners, backend developers, data engineers, and DevOps teams.
Follow best practices for testing, CI/CD, monitoring, documentation, and secure deployment.