Principal, Agentic Engineering Platform

What is The Role

AI is fundamentally transforming how professional services teams build and deliver value. At Elastic, we are focused on creating production-grade services platforms and software engineering practices that work reliably in real-world environments. The agentic engineering platform is a suite of tools designed to automate complex, multi-step delivery workflows across our global services organization.

We are looking for a Principal, Agentic Engineering Platform to lead this initiative end-to-end. In this role, you will design, ship, and refine agentic systems that directly support our services team. You will set technical standards, guide product strategy, and manage the complete life cycle: building, testing, deploying, monitoring, and iterating. While automated agents expand what you can deliver, you are the architect and decision-maker responsible for the final outcome. A key early priority is DIMA, Elastic's migration automation platform for SIEM and observability projects. Experience in security, SIEM, or observability will be highly valuable.

What You Will Be Doing

• Services Product Engineering & Platform Leadership:

  • Establish the technical vision and architectural standards for services agentic systems, ensuring automated tools enhance rather than replace engineering judgment.
  • Manage the platform roadmap and release schedule, overseeing stages from discovery and classification to quality assurance and rollout.
  • Develop multi-step workflows using LLM orchestration, tool integration, retrieval-augmented generation (RAG), and structured output processing.
  • Guide AI-assisted development workflows with tools like Claude Code and Codex, emphasizing issue-focused tasks, automated testing, and security reviews.
  • Design robust system architecture that addresses operational boundaries, potential failure modes, human approval steps, and long-term maintainability.

  Evaluation, Quality & Observability:

  • Create and maintain evaluation frameworks to assess agent performance across accuracy, reliability, response time, cost, and stability.
  • Implement tracing across tool calls, context assembly, and decision logic to troubleshoot and resolve production issues quickly.
  • Define quality benchmarks for professional services workflows and build system metrics to validate them.
  • Incorporate human review checkpoints wherever model output affects client deliverables or operational risk.

  Field Integration & Collaboration:

  • Ensure platform outputs generate clear evidence suitable for client deliverables, including proposals, statements of work, and project estimates.
  • Act as the key technical link between services platform engineering and delivery teams, working closely with stakeholders to seamlessly integrate agentic workflows into existing processes.
  • Partner with Services Practice Leads and the Global Specialist to turn operational strategies into practical tools.

What You Bring

• 10+ years of experience in platform engineering, software engineering, or technical professional services roles.
• Proven track record of deploying agentic or LLM-powered applications to production, with experience navigating the full deployment and optimization life cycle.
• Practical experience with LLM orchestration, prompt engineering, tool integration, and RAG architectures.
• Experience building evaluation systems, test suites, and monitoring tools for probabilistic models.
• Familiarity with developer tooling (such as Claude Code or Codex) and agent framework patterns.
• Strong Python engineering skills, with the ability to review backend services and data structures for production readiness.
• Focus on security best practices, including access control, least privilege, air-gapped setups, and safe handling of sensitive customer data.
• Strong communication skills, capable of explaining technical trade-offs and deployment risks to non-technical stakeholders.
• Willingness to travel up to 15% as needed.

Bonus Points

• Domain experience in SIEM, observability, or data migration (e.g., detections, ECS, Kibana Security, SPL).
• Familiarity with Elastic workflows, such as Kibana SIEM migrations, DIMA, or related migration tooling.
• Experience using Elasticsearch as a retrieval or search layer within agentic systems.
• Understanding of air-gapped environments and public-sector compliance requirements.
• Background in developing technical enablement or training programs for engineering teams.
• Relevant certifications across AI/ML, cloud platforms, or security technologies.