Honeycomb is hiring a Senior Software Engineer II to build production-grade AI agents for live observability analysis inside Canvas.

Design and deliver production-grade agents that investigate, reason, and act on live observability data inside Canvas.
Own agent delivery end-to-end: scope, build, ship, and maintain agents, including evals to confirm agents improve or meaningfully change behavior.
Build agent capabilities enabled by a data store that returns high-cardinality queries in seconds, so agents can correlate across services, drill into a single trace, and compare before/after deploys.
Extend Canvas and adjacent surfaces by shipping new capabilities into Canvas, the MCP server, and Canvas Skills memory.
Improve agent performance and iteration speed with a faster Bedrock loop, then propose what comes next with working code.
Set and uphold a bar for “good” agents using real evals, focusing on measurable quality, maintainability, and clarity about agent limits.

AI and agent engineering experience, including shipping LLM-based systems relied on in production (not demo-only) and understanding where agent systems break and how to design around it.
End-to-end ownership: take work from rough prototype through production-grade durable engineering without needing someone behind you to drive reliability.
Current judgment: informed opinions about changes in agent design over the last six to twelve months that would affect how you build today.
Agent architecture depth, including how a fast high-cardinality data store changes what agents can reason about and how to architect for it.
Product judgment: identify what the agent layer should do next and make the case with a prototype rather than a deck.

AI agents investigate, reason, and act on real observability data inside Canvas, the agentic workspace where engineers understand their systems.
The Agentic Intelligence team has shipped Canvas, the Honeycomb MCP server, and the Canvas Agent and Canvas Skills surfaces.
Some work may begin as a prototype, with expectations to carry code through the full arc to production-ready behavior.

Multiple agents collaborating on a shared Canvas investigation, each proposing a hypothesis, publishing findings, and narrowing the search space to resolve faster (blog).
Auto-investigation when an SLO burn alert fires: the agent forms hypotheses and prepares visualizations before a human looks, reducing mean-time-to-insight for on-call (o11ycon 2026).
Skills encoding team domain expertise (for example, Kubernetes thresholds) so agents and human colleagues can reuse that knowledge (o11ycon 2026).

Generous equity with an employee-friendly stock program
Unlimited PTO
Distributed-first mindset and culture
Home office, co-working, and internet stipend
Full benefits coverage for employees, with additional coverage available for dependents
Up to 16 weeks of paid parental leave, regardless of path to parenthood
Annual development allowance

Honeycomb cannot currently sponsor or support visa transfers at this time. In compliance with applicable law, all persons hired will be required to verify identity and eligibility to work.
Phishing warning: All communications will come from an @honeycomb.io email address. The recruiting process will never ask for financial or sensitive personal information such as Social Security or tax identification numbers, credit card numbers, or bank account information.
Diversity & accommodations: Honeycomb is committed to building a diverse, inclusive, and equitable workplace and will provide reasonable accommodations during the hiring process.
Privacy notice: If an application is unsuccessful (or you withdraw/decline), Honeycomb will retain your information for a period of time in accordance with local laws. For more information, see the Honeycomb Privacy Notice; contact [email protected] to opt out of retention for other roles or to update your information.

Senior Software Engineer II - Agentic Intelligence

Job Description