Agentic AI Engineer

Elastic, the Search AI Company, enables everyone to find the answers they need in real time, using all their data, at scale — unleashing the potential of businesses and people. The Elastic Search AI Platform, used by more than 50% of the Fortune 500, brings together the precision of search and the intelligence of AI to enable everyone to accelerate the results that matter. By taking advantage of all structured and unstructured data — securing and protecting private information more effectively — Elastic’s complete, cloud-based solutions for search, security, and observability help organizations deliver on the promise of AI. What is The Role The Elastic IT team is moving beyond simple chat to the next frontier: Agentic Workflows and Agent-to-Agent (A2A) Systems. We are looking for an innovative Agentic AI Engineer to join our team. You will build multi-agent ecosystems that are self-directed. These ecosystems will do more than just answer questions. They will collaborate, delegate tasks, and execute complex business processes across the organization. In this role, you will focus on large language models (LLMs), agent orchestration, and A2A integration frameworks to power our intelligent workforce. You will create workflows for multiple agents instead of just focusing on single-agent search or managing the stack. These workflows will enable the agents to communicate with each other, share information, access enterprise tools, and automate tasks from start to finish. Driven by a service-oriented mindset, you will empower internal teams with cutting-edge LLM capabilities while integrating seamlessly with enterprise systems. Are you ready to build the next generation of LLM-powered multi-agent systems that supercharge enterprise productivity? Join us to enable agent-to-agent workflows that turn collective knowledge into instant, coordinated action across Elastic. What You Will Be Doing • A2A Architecture & Multi-Agent Orchestration: Design, build, and deploy agent-to-agent (A2A) communication architectures and workflows that enable autonomous agents to collaborate, delegate tasks, and negotiate multi-step business processes. • LLM Integration & Tool Calling: Integrate advanced LLMs, both proprietary and open-source, with enterprise APIs. Use tool-calling methods. Connect with third-party SaaS applications for smooth operations. • Enterprise Grounding & RAG: Use advanced Retrieval-Augmented Generation (RAG) techniques. Implement strategies that connect enterprise context by using search and vector storage engines. This will ensure that all inter-agent operations are highly accurate and reliable. • Scalable Infrastructure & IaC: Provision and manage robust cloud environments (AWS, Azure, GCP) using Terraform to support the high-concurrency demands of LLM inferences and multi-agent coordination. • DevOps & Lifecycle Management: Support modern DevOps practices. This includes creating CI/CD pipelines for automated testing, deployment, and versioning. You will also evaluate LLMs and agentic workflows regularly. • A2A Security & Governance: Apply strict security and network fundamentals (VPC configurations, secure API gateways, encryption, and IAM controls) to secure inter-agent communication and protect sensitive enterprise data. • LLM Observability & Evaluation: Create systems to monitor how multiple agents interact. These systems will help us check model accuracy. They will also help manage token spending and identify model drift or agent loops. • Documentation: Keep detailed technical documents for LLM integration protocols. This includes A2A interaction flows and cloud infrastructure deployments. What You Bring • LLM & GenAI Expertise: Deep experience integrating, fine-tuning, and optimizing foundation models (e.g., OpenAI, Anthropic, open-source models), including expertise in prompt engineering, tool calling, and structured outputs. • Agent-to-Agent (A2A) Protocols: Proven success building multi-agent systems, inter-agent messaging pipelines, state management frameworks, and dynamic task delegation protocols. • Agentic Frameworks: Hands-on experience with multi-agent orchestration frameworks such as LangGraph, LangChain, AutoGen, etc. along with tracing platforms like LangSmith. • Market Trends & Interoperability: Strong understanding of emerging AI interoperability standards, such as the Model Context Protocol (MCP) and open multi-agent communication specifications. • Programming: Advanced proficiency in Python or TypeScript for backend orchestration, agent memory systems, and API service development. • Enterprise Grounding & Vector Search: Practical knowledge of RAG patterns, vector databases, hybrid search architectures, and context management strategies. • DevOps & Infrastructure as Code (IaC): Hands-on experience with DevOps practices and infrastructure automation using Terraform, Docker, and Kubernetes for scalable AI deployments. • Security & Network Fundamentals: Strong knowledge of secure cloud architectures, zero-trust network design, private endpoints, and identity management (OAuth, SAML, IAM) for secure A2A interactions. • LLM Observability & Evaluation: Experience setting up observability frameworks (logging, distributed tracing, and metrics) to track non-deterministic multi-agent workflows, token costs, and LLM output quality. • Enterprise AI Platform Knowledge: Knowledge of the broader agentic and workflow landscape (e.g., Workday A2A, Salesforce Agentforce, ServiceNow AI Agents). #LI-JM5 Compensation for this role is in the form of base salary. This role does not have a variable compensation component. The typical starting salary range for new hires in this role is listed below. In select locations (including Seattle WA, Los Angeles CA, the San Francisco Bay Area CA, and the New York City Metro Area), an alternate range may apply as specified below. These ranges represent the lowest to highest salary we reasonably and in good fa