2 months ago
United Kingdom (city not specified)Staff+
Responsibilities
- Own the production improvement loop for Context Engine by diagnosing agent, automation, retrieval, and memory behavior and measuring fixes.
- Define safe iteration practices for prompts, skills, automations, versioning, rollouts, regression coverage, and staged or shadow evaluations.
- Design telemetry for agent traces, tool calls, and knowledge retrieval, and connect it to Elasticsearch, evaluations, dashboards, and feedback loops.
- Partner with data scientists on golden datasets and evaluators for quality, latency, and cost.
- Run product experiments end to end, including instrumentation, unattended execution, and interpretation of results.
- Review designs and pull requests, mentor engineers in eval-driven development, and write technical proposals that shape the roadmap.
Requirements
- 10+ years of software engineering experience, including recent experience shipping and operating AI-driven products on real production traffic.
- Demonstrated experience diagnosing agent or LLM behavior using traces and user feedback, designing evaluations, shipping fixes, and measuring outcomes.
- Direct experience building agents with state and memory and safely iterating on prompts, skills, and tool behavior in production.
- Experience with MCP, including exposing public MCP servers and tools.
- Experience designing telemetry for AI systems and using it for engineering and product decisions.
- Experience building products with public APIs and evolving data models without breaking external customers.
- Strong backend engineering skills in Python or TypeScript, including APIs, stateful workflows, data pipelines, and production services.
- Ability to collaborate with data scientists, engineers, and product managers and communicate technical trade-offs clearly.
- Experience with agent frameworks such as LangGraph, CrewAI, or Claude Agent SDK is a bonus.
- Agentic retrieval, knowledge representation, and practical Elasticsearch experience are bonus qualifications.
Benefits
- Health coverage for employees and families in many locations.
- Flexible locations and schedules with the ability to craft calendars for many roles.
- Generous vacation allowance.
- Elastic matches up to $2,000, or local currency equivalent, for financial donations and provides up to 40 volunteer hours annually.
- At least 16 weeks of parental leave.
- Distributed, async-first work environment with benefits designed for regional parity.
Tech Stack
Categories
About Elastic
Elastic builds the Elasticsearch-based platform for enterprise search, observability (logging, metrics, APM), and security (SIEM/endpoint). It sells subscriptions and Elastic Cloud managed services with usage-based pricing, combining open source and proprietary features through Elasticsearch and Kibana. Founded in 2012 and headquartered in San Francisco, Elastic is publicly traded on the NYSE and is used by more than half of the Fortune 500.