Opportunity at
ElasticPrincipal, Agentic Engineering Platform
This full-time principal role is on-site in the United States and leads the Agentic Engineering Platform, a suite of tools that automates multi-step delivery work for…
Career Tools
About This Role
This full-time principal role is on-site in the United States and leads the Agentic Engineering Platform, a suite of tools that automates multi-step delivery work for Elastic's global services organization. The platform is meant to support services teams with production-grade agentic systems. Early work centers on DIMA, the in-house tool that automates migration projects in SIEM and observability, so background in those security or monitoring areas counts for a lot.…
Job Description
This full-time principal role is on-site in the United States and leads the Agentic Engineering Platform, a suite of tools that automates multi-step delivery work for Elastic's global services organization. The platform is meant to support services teams with production-grade agentic systems. Early work centers on DIMA, the in-house tool that automates migration projects in SIEM and observability, so background in those security or monitoring areas counts for a lot.
The principal defines the technical direction and architecture rules for services agent systems and keeps automation as an aid to, not a substitute for, engineering judgment. The role is accountable for the platform's roadmap and release calendar, covering every stage from initial discovery to classification, QA and deployment. Construction covers chained LLM workflows, external tool hookups, retrieval-augmented generation and structured results, plus AI-assisted coding habits built around Claude Code and Codex.
Evaluation and observability are central. Evaluation frameworks track correctness, dependability, latency, spend and steadiness, tracing follows each tool invocation and branching decision, and benchmarks set the quality bar for services work. Human review checkpoints are required wherever model output could affect client deliverables or operational risk. Results need to yield documentation that stands up in proposals, SOWs and estimates.
The role links platform engineering with delivery teams and works with services practice leads to turn operating strategies into tools. Security is a stated concern, including access control, least privilege, isolated deployments and careful handling of customer data. Travel of up to 15 percent may be needed. The employer describes itself as a search AI company used by more than half of the Fortune 500.
Responsibilities
- Set the technical vision and architecture standards for services agentic systems
- Own the product plan and release calendar for the platform through discovery, quality assurance and rollout
- Build multi-step workflows with LLM orchestration, tool integration, RAG and structured outputs
- Guide AI-assisted development with Claude Code and Codex, emphasizing testing and security reviews
- Design system architecture that handles failure modes, human approvals and long-term maintenance
- Create evaluation frameworks and tracing across tool calls and decision logic
- Define quality benchmarks for services workflows and add human review checkpoints where needed
- Work with the services practice leads and delivery teams to fold agentic workflows into current processes
Requirements
- Ten-plus years in platform work, software engineering or technical services delivery
- History of putting agent-driven or LLM-based applications into production
- Hands-on skill with LLM orchestration, prompt design, tool wiring and RAG architectures
- Know-how building eval harnesses, test coverage and monitoring for non-deterministic models
- Comfort with developer tooling like Claude Code or Codex, plus agent framework patterns
- Strong Python engineering skills for reviewing backend services and data structures
- Security-minded approach covering access control, least privilege, isolated (air-gapped) deployments and careful handling of sensitive client data
- Able to convey technical compromises and deployment hazards to people outside engineering
- Available to travel up to about 15 percent of the time
Qualifications
- Background in SIEM, observability or migration projects, covering detections, ECS, Kibana Security and SPL
- Exposure to Kibana SIEM migration work, DIMA or comparable migration utilities
- Elasticsearch deployed as the search or retrieval backbone for agent systems
- Understanding of isolated environments and public-sector compliance
- Experience creating enablement or training tracks for engineering teams
Core Skills
Benefits
- Pay set by the scope of the work rather than past salary
- Medical coverage for staff and their families in many regions
- Choice of location and working hours for many positions
- Generous annual vacation allowance
- Matching for charitable giving and service of up to $2,000 in local currency equivalent, plus up to 40 hours a year for volunteer projects
- Parental leave of at least 16 weeks
Frequently Asked Questions
Answers are based only on the employer’s listing; where it doesn’t say, neither do we.
Is this role on-site?
Yes. The listing is marked on-site and the location is United States.
What is the base salary range?
The typical starting base salary range is 159,800 to 252,800 USD. In select locations the range is 191,900 to 303,500 USD. The posting states there is no variable compensation component.
Is travel required?
Travel of up to 15 percent may be needed.
What is DIMA?
DIMA is a tool Elastic uses to automate migrations for SIEM and observability projects, and the posting names it as an early task for this role.
Sample Interview Questions
AI-generated questions tailored to this specific role — a preview of the full practice set.