Principal AI Engineer - Context - Agents and Context
Job description
Principal AI Engineer on Elastic's Context Engine team, owning the production improvement loop for the knowledge layer AI agents use with enterprise data in Elasticsearch. The role spans engineering, data science and product, writing production TypeScript code and designing evaluation and telemetry for agentic behaviour.
At a glance
- Employment
- Full-time · Employee (employment agreement)
- Work mode
- Hybrid
- Languages
- English
What you'll do
- Own the production improvement loop for Context Engine: understand how extraction automations, retrieval tools and memory behave, based on offline evaluations, customer conversations and telemetry; find failure modes, fix them, and prove the fix
- Define how the team iterates on agents and skills safely: versioning and rollout of prompts, skills and automations, regression coverage, staged and shadow evaluation, and guardrails
- Design telemetry for data-informed engineering decisions: what to capture 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 the data science team on evaluation strategy: golden datasets, evaluators to gate on quality, latency and cost
- Raise the bar across the team: review designs and PRs, mentor engineers in eval-driven development, and write technical proposals that shape the roadmap
What we're looking for
- 10+ years of software engineering experience, with recent years spent shipping and operating AI-driven products on real production traffic, ideally products with public APIs and data models that had to evolve without breaking customers
- A track record of eval-driven product improvement: diagnosing agent or LLM behaviour from traces and user feedback, designing the evaluation that exposed the problem, shipping the fix and measuring the outcome
- Direct experience building agents with state and memory, and iterating on prompts, skills and tool behaviour safely in production
- Ability to explain how tool calls and their results flow through each iteration, how context grows across turns and how it is managed, and how the loop decides to stop
- Familiarity with MCP, including exposing public MCP servers and tools
- Experience designing telemetry for AI systems, and using it to make engineering and product decisions
- Experience running product experiments end to end: instrumentation, unattended execution, and interpreting results
- Experience building products with public APIs and evolving data models, and maintaining external contracts as a product changes
- Strong backend engineering skills in either Python or TypeScript: APIs, stateful workflows, data pipelines and production services
- Comfort working with data scientists, engineers, and product managers as peers, translating between measurement and shipping, and communicating trade-offs clearly
- A pragmatic, low-ego style suited to a distributed, async-first team
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
Your team
Context Engine team
Builds the knowledge layer that AI agents use to work with enterprise data in Elasticsearch: extracting knowledge from data sources into a structured AI Index, serving it to agents through public APIs, MCP tools and framework integrations, and closing the loop with agent traces.
Benefits
- Competitive pay based on the work you do here and not your previous salary
- Health coverage for you and your family in many locations
- Ability to craft your calendar with flexible locations and schedules for many roles
- Generous number of vacation days each year
- We match up to $2000 (or local currency equivalent) for financial donations and service
- Up to 40 hours each year to use toward volunteer projects you love
- Minimum of 16 weeks of parental leave
Apply
About Elastic
The Search AI Company
Elastic enables everyone to find the answers they need in real time, using all their data, at scale. The Elastic Search AI Platform, used by more than 50% of the Fortune 500, brings together the precision of search and the intelligence of AI, with complete, cloud-based solutions for search, security, and observability.
Key facts
- Search AI / software
- The Elastic Search AI Platform is used by more than 50% of the Fortune 500
- Elastic builds in the open alongside the rest of the Elastic Stack
- Elastic is a distributed company
What they value
- Diversity drives our identity
- Balance great work with great life
- Parity of benefits across regions
- Taking care of our people