Principal, Agentic Engineering Platform
$160k - $304k • Remote • United States
Posted 16d ago
Job Location
United States
Tech Stack
Remote Work Policy
Fully remote
Categories
AI Agent Engineer
About the job
Elastic is seeking a Principal, Agentic Engineering Platform to lead the development and refinement of agentic systems that automate complex, multi-step delivery workflows for their global services organization. This role involves setting technical standards, guiding product strategy, and managing the entire lifecycle of building, testing, deploying, monitoring, and iterating on these systems. A key initial focus will be on DIMA, Elastic's migration automation platform for SIEM and observability projects. Experience in security, SIEM, or observability will be highly valuable.
Responsibilities
- Establish technical vision and architectural standards for services agentic systems.
- Manage the platform roadmap and release schedule.
- Develop multi-step workflows using LLM orchestration, tool integration, RAG, and structured output processing.
- Guide AI-assisted development workflows with tools like Claude Code and Codex.
- Design robust system architecture addressing operational boundaries, failure modes, and human approval steps.
- Create and maintain evaluation frameworks for agent performance.
- Implement tracing for troubleshooting production issues.
- Define quality benchmarks for professional services workflows and build system metrics.
- Incorporate human review checkpoints for model outputs affecting client deliverables or risk.
- Ensure platform outputs generate clear evidence for client deliverables.
- Act as a technical link between services platform engineering and delivery teams.
- Partner with Services Practice Leads and the Global Specialist to translate strategies into tools.
Requirements
- 10+ years of experience in platform engineering, software engineering, or technical professional services.
- Proven track record of deploying agentic or LLM-powered applications to production.
- 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 (e.g., Claude Code, Codex) and agent framework patterns.
- Strong Python engineering skills.
- Focus on security best practices.
- Strong communication skills to explain technical trade-offs to non-technical stakeholders.
- Willingness to travel up to 15%.