Principal AI Engineer - Context - Agents and Context

Elastic is a company specializing in Search AI solutions used by more than 50% of the Fortune 500. Its product, the Elastic Search AI Platform, integrates search precision with AI intelligence to enable real-time data insights at scale. The Context Engine team focuses on building the knowledge layer that AI agents use to work with enterprise data in Elasticsearch.

• 10+ years of software engineering experience with recent experience shipping and operating AI-driven products on production traffic.
• Proven track record of evaluation-driven product improvement diagnosing agent or LLM behavior from traces and user feedback.
• Direct experience building agents with state and memory and iterating on prompts, skills, and tool behavior safely in production.
• Familiarity with MCP, including exposing public MCP servers and tools.
• Experience designing telemetry for AI systems to support engineering and product decisions.
• Experience running product experiments end to end including instrumentation and interpretation of results.
• Experience building products with public APIs and evolving data models.
• Strong backend engineering skills in Python or TypeScript encompassing APIs, stateful workflows, data pipelines, and production services.
• Ability to collaborate effectively with data scientists, engineers, and product managers.
• Pragmatic, low-ego style suited for distributed, asynchronous teams.

Nice to have:

• Experience with agent frameworks such as LangGraph, CrewAI, Claude Agent SDK, or similar.
• Agentic retrieval experience including knowledge representation.
• Practical Elasticsearch experience.

• Own the production improvement loop for Context Engine: analyze extraction automations, retrieval tools, and memory behavior, identify failure modes, implement fixes, and verify outcomes.
• Define safe iteration processes for agents and skills, including versioning, rollout, regression coverage, and evaluation guardrails.
• Design telemetry capturing agent traces, tool calls, and knowledge retrieval to inform engineering decisions.
• Partner with data science on evaluation strategy involving datasets and quality gating.
• Review designs and pull requests, mentor engineers in evaluation-driven development, and write technical proposals shaping the roadmap.

Employment eligibility is not affected by national origin or nationality. Export controls apply for individuals located in or nationals of Belarus, Cuba, Iran, North Korea, Syria, Russia, and certain Ukrainian territories annexed by Russia. Accommodation requests are welcomed. Equal opportunity employer committed to diversity and inclusion.