Agentic AI Engineer - Elastic

Elastic, the Search AI Company, enables organizations to find answers in real time using all their data at scale. The Elastic Search AI Platform combines search precision with AI intelligence to accelerate critical results across search, security, and observability.

What is the Role

The Elastic IT team is expanding beyond conversational chat to build agentic workflows and agent-to-agent (A2A) systems. As an Agentic AI Engineer, you will design and implement self-directed multi-agent ecosystems that collaborate, delegate tasks, and execute complex business processes across the enterprise.

You will focus on large language models (LLMs), agent orchestration, and A2A integration frameworks to power Elastic's intelligent workforce, connecting enterprise tools and automating workflows end-to-end.

What You Will Be Doing

• A2A Architecture & Multi-Agent Orchestration: Design, build, and deploy agent-to-agent (A2A) communication architectures and workflows enabling autonomous agents to collaborate, delegate tasks, and negotiate multi-step processes.
• LLM Integration & Tool Calling: Integrate advanced proprietary and open-source LLMs with enterprise APIs, tool-calling mechanisms, and SaaS applications.
• Enterprise Grounding & RAG: Implement advanced Retrieval-Augmented Generation (RAG) and hybrid search architectures using vector engines to ensure accurate, context-grounded agent operations.
• Scalable Infrastructure & IaC: Provision and manage cloud environments (AWS, Azure, GCP) using Terraform to support high-concurrency LLM inference and agent coordination.
• DevOps & Lifecycle Management: Build CI/CD pipelines for automated testing, deployment, evaluation, and versioning of LLMs and agentic workflows.
• A2A Security & Governance: Apply zero-trust network design, VPC configurations, secure API gateways, encryption, and IAM controls to secure inter-agent communications.
• LLM Observability & Evaluation: Build observability frameworks to monitor agent interactions, token usage, model accuracy, and detect drift or agent loops.
• Documentation: Maintain comprehensive technical documentation for LLM integration protocols, A2A interaction flows, and cloud infrastructure.

What You Bring

• LLM & GenAI Expertise: Deep experience integrating, fine-tuning, and optimizing foundation models (OpenAI, Anthropic, open-source), prompt engineering, tool calling, and structured outputs.
• Agent-to-Agent (A2A) Protocols: Proven experience building multi-agent systems, inter-agent messaging pipelines, state management frameworks, and task delegation protocols.
• Agentic Frameworks: Hands-on experience with orchestration frameworks like LangGraph, LangChain, AutoGen, and tracing tools like LangSmith.
• Market Trends & Interoperability: Strong understanding of emerging AI interoperability standards such as Model Context Protocol (MCP) and open multi-agent specifications.
• Programming: Advanced proficiency in Python or TypeScript for backend orchestration, agent memory systems, and API development.
• Enterprise Grounding & Vector Search: Practical knowledge of RAG patterns, vector databases, hybrid search architectures, and context management.
• DevOps & IaC: Experience with infrastructure automation using Terraform, Docker, and Kubernetes for scalable AI deployments.
• Security & Network Fundamentals: Strong knowledge of secure cloud architectures, private endpoints, and identity management (OAuth, SAML, IAM).
• LLM Observability & Evaluation: Experience implementing logging, distributed tracing, and metrics to monitor non-deterministic multi-agent workflows and token costs.
• Enterprise AI Platform Knowledge: Familiarity with the enterprise agentic landscape (e.g., Workday A2A, Salesforce Agentforce, ServiceNow AI Agents).