Elastic
Agentic AI Engineer
About this role
Elastic seeks an Agentic AI Engineer to design and deploy autonomous, enterprise-focused AI agents that execute complex business workflows. You'll leverage the Elastic Stack, LLMs, and cloud infrastructure to build intelligent systems that enhance organizational productivity while becoming a subject matter expert on Elastic's platform.
What you'll do
- Design and implement sophisticated agentic workflows using reasoning engines and tool integration for end-to-end business processes
- Ground agents in enterprise knowledge using RAG and Elasticsearch Relevance Engine (ESRE) for accurate task completion
- Develop and integrate LLMs with internal APIs and third-party tools to enable autonomous action
- Provision and manage cloud infrastructure on AWS, Azure, or GCP using Terraform and modern DevOps practices
- Implement comprehensive observability and monitoring systems to track agent performance, latency, and model drift
- Apply security best practices including VPC configurations, encryption, IAM controls, and compliance standards
What they're looking for
- Agentic AI frameworks (LangGraph, LangChain, LangSmith)
- Retrieval Augmented Generation (RAG) and Elasticsearch Relevance Engine
- LLM fine-tuning and integration
- Infrastructure as Code (Terraform, Docker, Kubernetes)
- Cloud platforms (AWS, Azure, GCP)
- DevOps and CI/CD pipeline design
- Security and network architecture (VPC, OAuth, SAML, IAM)
- Observability and distributed tracing systems
Opens the official application on the employer’s site. No login required.
Elastic
Elastic builds and operates multi-cloud infrastructure and observability platforms that power Elastic Cloud across 70+ regions. The company is hiring Platform Engineers and Site Reliability Engineers to design Kubernetes-based systems, develop automation tools, optimize cloud infrastructure, and ensure reliable operations at scale.
- Website
- elastic.co
Likely interview questions
- Describe a GenAI project where you built autonomous agents to complete complex workflows end-to-end. What frameworks did you use and what challenges did you overcome?
- How have you implemented RAG systems in production, and what strategies did you use to ensure agents remained grounded in accurate enterprise knowledge?