- Workplace
- Remote
- Type
- Full-time
- Level
- Senior
- Salary
- Not listed
Little more about the team:
AI agents at Honeycomb investigate, reason, and act on real observability data. They live in Canvas: the agentic workspace where engineers go to understand their systems.
The Agentic Intelligence team has shipped Canvas, the Honeycomb MCP server, and the Canvas Agent and Canvas Skills surfaces. What we're looking for today is someone who brings deep agent expertise and uses it to expand what the team can build: new agents, new surface area in Canvas, memory, spatial awareness, improved performance on our Bedrock loop.
Honeycomb's data store is fast and accepts high cardinality data; that's what makes agents built on top of it different from anything built on a conventional observability backend. This role is about taking advantage of that building agents that can do things no other observability product can do because the underlying data makes it possible.
Some of this work will start as a prototype. The expectation is that the code makes it through the full arc, from the rough first version through to something that holds up in production.
What you'll do
- Design and deliver production-grade agents. Build agents that investigate, reason, and act on live observability data inside Canvas. These agents must be trustworthy to engineers in high pressure situations, including mid-incident. Take one from rough first version to something that holds up under production traffic.
- Own the agent work; support the whole product. Scope, build, ship, and maintain the agents including the evals that tell you whether they got better or are just different. This role is agent-focused and also includes some fullstack development.
- Build agents only Honeycomb can build. Use a data store that returns high-cardinality queries in seconds to reason over signal a conventional backend can't serve at this fidelity correlating across services, drilling into a single trace, comparing before and after a deploy.
- Extend the surface, and decide what's next. Ship new capability into Canvas, the MCP server, and Canvas Skills memory, spatial awareness, a faster Bedrock loop and make the case for what comes after with working code. Distinguish hype from signal in a field with plenty of both.
- Define what "good" means for agents here. Set the bar: measurable against real evals, maintainable, and honest about their limits.
Example projects
- Multiple agents collaborating on one shared Canvas investigation each claiming a hypothesis, publishing findings, and narrowing the search space for the others so it resolves faster (blog).
- Auto-investigation the moment an SLO burn alert fires the agent forms hypotheses and prepares visualizations before a human looks, cutting mean-time-to-insight for on-call (o11ycon 2026).
- Skills that encode a team's domain expertise e.g. Kubernetes thresholds so agents and human colleagues can lean on them (o11ycon 2026).
What you'll bring:
- AI and agent engineering experience. You've shipped LLM-based systems people relied on in production not demos, not fine-tuned models in a research context. You know where agent systems break and how to design around it.
- End-to-end ownership. On a small team there's no handoff queue. You can take something from rough prototype to production-grade without needing someone behind you to do the durable engineering.
- Current judgment, not just past experience. You have informed opinions about what's shifted in agent design in the last six to twelve months that would change how you'd build today.
- Agent architecture depth. You understand how a fast, high-cardinality data store changes what an agent can reason about, and how to design for that.
- Product judgment. You can look at what the agent layer does today and see what it should do next and make that case with a prototype, not a deck.
Even better
Observability or developer-tools background. Engineers are your users; you'll ramp faster with fluency in that world, and the work is better.
Familiarity with eval frameworks, agent tooling, RAG, and prompt engineering.
Base Salary based on level of experience$250,000â$280,000 CADWhat you'll get when you join the Hive:
- A stake in our success - generous equity with employee-friendly stock program
- Itâs not about how strong of a negotiator you are - our pay is based on transparent levels relative to experience
- Time to recharge with unlimited PTO
- A distributed-first mindset and culture (really!)
- 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 allowanceÂ
- And much more...
- All communications will come from an @honeycomb.io email address
- We occasionally work with external recruiting agencies. These partners will use legitimate business email addressesânever personal accounts like Gmail or Yahoo.
- Our recruiting process will never ask you to provide financial or sensitive personal information, including but not limited to:
- Social security or tax identification numbers
- Credit card numbers
- Bank account information
Â
Diversity & Accommodations: We're committed to building a diverse, inclusive, and equitable workplaceâwhere people of all backgrounds, identities, experiences, and abilities are welcomed, valued, and supported. We recognize that there is no single path to success and embrace nontraditional career journeys and diverse perspectives as key to building stronger, more innovative teams.  We strive to ensure an inclusive experience throughout every stage of our hiring process and are happy to provide reasonable accommodations as needed. If you require accommodations or accessible formats at any point during our hiring process, please let your recruiter know.  As an equal opportunity employer our hiring process is designed to put you at ease and help you show your best work. If thereâs anything we can do to improve your experience, weâre always open to feedback.   Privacy Notice: If you apply for a job at Honeycomb and your application is unsuccessful (or you withdraw from the process or decline our offer), Honeycomb will retain your information after your application for a period of time in accordance with local laws. We retain this information for various reasons, including in case we face a legal challenge in respect of a recruitment decision, to consider you for other current or future jobs at Honeycomb, and to help us better understand, analyze and improve our recruitment processes.  For more information regarding our privacy practices please see the Honeycomb Privacy Notice.  If you do not want us to retain your information, or want us to update it, please contact privacy@honeycomb.io. Please note, however, that we may retain some information if required by law or as necessary to protect ourselves from legal claims.ÂPlease mention the word **PERSONALIZED** and tag RMTM0LjEzOC40NC4xNjU= when applying to show you read the job post completely (#RMTM0LjEzOC40NC4xNjU=). This is a beta feature to avoid spam applicants. Companies can search these words to find applicants that read this and see they're human.
JobsPing insights
Our own analysis of this role, based on every open job we track. Updated daily.
Salary benchmark
Software Engineering roles in Canada · 35 posted USD salaries
This listing doesn’t publish a USD salary. Use this range as a starting point when you discuss pay. How to negotiate
How in-demand these skills are
Share of all open roles on JobsPing that ask for each skill
- LLM / GenAI15% · 1,405
- Kubernetes8.1% · 760
Honeycomb.io right now
- Open roles
- 1
- Remote
- 100%
- New this week
- 1
Skills they ask for most: Kubernetes, LLM / GenAI.
How to stand out for this role
- Lead your resume bullets with shipped outcomes: latency cut, revenue moved, incidents reduced.
- Link one repository or project that uses this job’s main stack, and make sure its README explains what you built.
- Mirror the posting’s exact tool names (e.g. “PostgreSQL”, “Next.js”) for skills you genuinely have.
- Prepare one story about a production bug you debugged end-to-end; it comes up in almost every loop.
This job was originally posted on Remote OK.