Senior AI Engineer – Context Engine & Agent Telemetry

Elastic; Greater London; Hybrid; GBP 120,000 - 190,000; Full time

Benefits offered by this job

Health coverage for you and family

Flexible location and schedule

Generous vacation days

Parental leave (16 weeks) and family 


Volunteer time (40 hours/year)

Charitable giving matching

Job summary

Elastic’s Context Engine team builds the knowledge layer used by AI agents to work with enterprise data in Elasticsearch. We extract knowledge from any data sources into a structured AI Index and expose it to agents through public APIs, MCP tools and framework integrations.

As a Principal AI Engineer, you own the end-to-end production improvement loop: how agents, automations and skills behave, how we observe and evaluate them, and how we ship changes safely.

Qualifications

• Track record of eval-driven product improvement and diagnosing agent/LLM behaviour from traces and feedback.
• Strong backend engineering skills in Python or TypeScript: APIs, stateful workflows, data pipelines.
• Experience running product experiments end to end: instrumentation and interpreting results.
• Experience building agents with state and memory, iterating on prompts, skills and tool behavior in production.
• Experience designing telemetry for AI systems to inform engineering and product decisions.
• Experience with agent frameworks such as LangGraph, CrewAI, Claude Agent SDK or similar.
• Experience with public APIs and evolving data models while maintaining external contracts.
• Practical Elasticsearch experience.

Responsibilities

• Own the production improvement loop for Context Engine: understand extraction automations, retrieval tools and memory behaviour.
• Define iteration on agents and skills safely: versioning, rollout, regression coverage and guardrails.
• Design telemetry to support data-informed engineering decisions: traces, tool calls, knowledge retrieval, dashboards.
• Collaborate with data science to shape evaluation strategies and gate on quality metrics.
• Review designs and PRs, mentor engineers in evaluation-driven development, contribute to the roadmap.

Skills

Backend engineering

Public APIs

Elasticsearch

Agent frameworks

Eval-driven development

Telemetry design

Data science collaboration

Production deployment

Tools

LangGraph

Claude Agent SDK

CrewAI

LangChain

Job description

Elastic’s Context Engine team builds the knowledge layer used by AI agents to work with enterprise data in Elasticsearch. We extract knowledge from any data sources into a structured AI Index and expose it to agents through public APIs, MCP tools and framework integrations.

As a Principal AI Engineer, you own the end-to-end production improvement loop: how agents, automations and skills behave, how we observe and evaluate them, and how we ship changes safely.