Principal AI Engineer - Context - Agents and Context
About this role
Engineers who thrive on building foundational layers for artificial intelligence and driving rigorous evaluation loops will find a natural home in this role. The Context Engine team at Elastic constructs the knowledge layer that intelligent agents use to interact with enterprise data in Elasticsearch, serving information through public APIs, MCP tools, and framework integrations.
Working at the intersection of engineering, data science, and product, the incoming Principal AI Engineer will own the end-to-end product improvement loop. Responsibilities include shaping how extraction automations, retrieval tools, and memory behave in production, designing telemetry and evaluation frameworks, and setting the technical bar for agentic iteration. The codebase relies on TypeScript, and the team operates in the open as part of the broader Elastic Stack.
What you will do
- Manage the production improvement loop for the Context Engine by analyzing offline evaluations, customer telemetry, and user feedback.
- Establish safe iteration practices for agents and skills, including prompt versioning, regression coverage, and staged evaluations.
- Design telemetry systems to capture agent traces, tool calls, and knowledge retrieval metrics inside Elasticsearch.
- Collaborate with data science teams to build golden datasets and define quality, latency, and cost evaluators.
- Mentor engineers in evaluation-driven development, review design proposals, and guide the technical roadmap.
- Write production-grade code in TypeScript or Python while maintaining external contracts for public APIs.
What you need
- Ten or more years of software engineering experience, featuring recent work operating AI-driven products on live production traffic.
- Demonstrated track record of evaluation-driven product improvement for LLMs or autonomous agents.
- Direct background in building stateful agents with memory and safely iterating on prompt and tool behavior in production environments.
- Familiarity with the Model Context Protocol, including the publication of public MCP servers and tools.
- Experience designing telemetry for AI systems to inform engineering and product decisions.
- Strong backend engineering proficiency in Python or TypeScript, covering stateful workflows and APIs.
Nice to have
- Experience with agent frameworks such as LangGraph, CrewAI, or the Claude Agent SDK
- Agentic retrieval experience including knowledge representation
- Practical Elasticsearch experience
Benefits
- Stock program participation
- Company-matched RRSP up to 6% of eligible earnings
- Health coverage for employee and family
- Flexible locations and schedules
- Generous annual vacation days
- Minimum 16 weeks of parental leave
Skills and tech stack
Questions candidates ask
What is the remote work policy for this role?
This is a hybrid role with flexible locations and schedules available for many positions within Elastic's distributed, async-first team structure.
What is the salary range for this position?
The typical starting base salary range for new hires is $154,000 to $243,600 CAD. Additionally, this role is eligible to participate in the company stock program and other total rewards benefits.
What technologies and languages are used in the codebase?
The primary codebase is built in TypeScript, with backend engineering tasks also supporting Python. The team builds products around Elasticsearch, public APIs, and MCP tools.
What team will this engineer work within?
The person in this role joins the Context Engine team, working alongside data scientists, backend engineers, product managers, and UX designers.