Honeycomb.io

Senior Software Engineer II - Agentic Intelligence

Honeycomb.io
Apply
2 months ago
Remote, United StatesSenior

Base Salary

$183k - $206k/yr

Responsibilities

  • Design and deliver production-grade agents that investigate, reason over, and act on live observability data in Canvas.
  • Own agent development end to end, including scoping, building, shipping, maintaining, and creating evaluations.
  • Use Honeycomb’s high-cardinality data store to build observability agents with capabilities conventional backends cannot support.
  • Extend Canvas, the MCP server, and Canvas Skills with capabilities such as memory, spatial awareness, and improved Bedrock-loop performance.
  • Define measurable standards for agent quality, maintainability, and limitations.
  • Contribute to full-stack development and make product-direction recommendations through working prototypes.

Requirements

  • Experience shipping LLM-based agent systems that people relied on in production, rather than demos or research-only fine-tuned models.
  • Ability to take systems from rough prototypes to durable, production-grade implementations with end-to-end ownership.
  • Deep understanding of agent architecture and how fast, high-cardinality data stores affect agent reasoning.
  • Current knowledge and informed opinions about recent changes in agent design.
  • Strong product judgment and ability to identify and prototype the next capabilities for an agent layer.

Benefits

  • Fully distributed and remote work arrangement.
  • Generous equity with an employee-friendly stock program.
  • Unlimited paid time off.
  • Home office, coworking, and internet stipend.
  • Full benefits coverage for employees, with additional dependent coverage available.
  • Up to 16 weeks of paid parental leave regardless of path to parenthood.
  • Annual development allowance.

Tech Stack

Categories

Honeycomb.io

About Honeycomb.io

201-500 employees

Honeycomb.io builds a SaaS observability platform for software engineering, SRE, and DevOps teams to debug and operate distributed systems using tracing, event data, and high-cardinality queries. Its product integrates with OpenTelemetry and supports SLOs, instrumentation, and production debugging workflows. Founded in 2016 and headquartered in San Francisco, the company is privately held and counts customers such as Slack, HelloFresh, LaunchDarkly, and Vanguard.

Contact me