Principal AI Engineer - Context, Agents and Context

About the role

The Context Engine team builds the knowledge layer that AI agents use to work with enterprise data in Elasticsearch, extracting knowledge from any data source into a structured AI Index and serving it via public APIs, MCP tools and framework integrations. As a Principal AI Engineer you own the end-to-end improvement loop: how agents, automations and skills behave in production, how they are observed and evaluated, and how changes are shipped safely. This is a hybrid role at the intersection of engineering, data science and product, working alongside data scientists, backend engineers, product and UX teams.

Key responsibilities

• Own the production improvement loop: understand how extraction automations, retrieval tools and memory behave from offline evaluations, customer conversations and telemetry, find failure modes and prove fixes.
• Define safe iteration on agents and skills: versioning and rollout of prompts, skills and automations, regression coverage, staged and shadow evaluation, and guardrails.
• Design telemetry from agent traces, tool calls and knowledge retrieval, how it lands in Elasticsearch and how it feeds evaluation, dashboards and the feedback loop.
• Partner with data science on evaluation strategy, including golden datasets and evaluators for quality, latency and cost.
• Raise the bar across the team by reviewing designs and PRs, mentoring engineers in eval-driven development and writing technical proposals for the roadmap.

Required profile

• 10+ years of software engineering experience, recently shipping and operating AI-driven products on real production traffic, ideally with public APIs and evolving data models.
• Track record of eval-driven product improvement: diagnosing agent or LLM behaviour from traces and user feedback, designing the evaluation, shipping the fix and measuring the outcome.
• Experience building agents with state and memory, and iterating on prompts, skills and tool behaviour safely in production.
• Experience running product experiments end to end and building products with public APIs.
• Strong backend engineering skills in Python or TypeScript.

Required skills

• Familiarity with MCP, including exposing public MCP servers and tools.
• Experience designing telemetry for AI systems.
• Bonus: agent frameworks such as LangGraph, CrewAI or Claude Agent SDK, agentic retrieval, practical Elasticsearch experience.

What we offer

• Base salary of EUR 73,300 to 115,900, with no variable component.
• Flexible locations and schedules, generous vacation days, health coverage for you and your family in many locations.
• Company matching of up to $2,000 for donations and service, and up to 40 hours per year for volunteering.
• Minimum of 16 weeks of parental leave.