Senior Software Engineer II - Agentic Intelligence

div class= content-intro div strong What We’re Building /strong /div

div Honeycomb is a service for the near and present future, defining observability and raising expectations of what developer tools can do! We’re working with well known companies like HelloFresh, Slack, LaunchDarkly, and Vanguard and more across a range of industries. This is an exciting time in our trajectory, we’ve closed Series D funding, scaled past the 200-person mark, and were named to Forbes’ America’s Best Startups of 2022 and 2023! /div

div /div

div If you want to see what we’ve been up to, please check out these a href= https://www.honeycomb.io/blog target= _blank blog posts /a and Honeycomb.io a href= https://www.honeycomb.io/category/press-releases target= _blank press releases /a . /div

div /div

div strong Who We Are /strong /div

div We come for the impact, and stay for the culture! We’re a talented, opinionated, passionate, fiercely inclusive, and responsible group of bees. We have conviction and we strive to live a class= postings-link href= https://www.honeycomb.io/about/ target= _blank u our values /u /a every day. We want our people to do what they truly love amongst a team of highly talented (but humble) peers. /div

div /div

div strong How We Work /strong /div

div We are a fully distributed company, which means we believe it is not where you sit, but how you deliver that matters most. We invest in our people and care about how you orient to our culture and processes. At the same time we imbue a lot of trust, autonomy, and accountability from Day 1. #LI-Remote /div /div h4 class= text-text-100 mt-3 -mb-1 text-[1.125rem] font-bold About the role /h4

p class= font-claude-response-body break-words whitespace-normal 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. /p

p class= font-claude-response-body break-words whitespace-normal 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. /p

p class= font-claude-response-body break-words whitespace-normal 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. /p

p class= font-claude-response-body break-words whitespace-normal 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. /p

h4 class= text-text-100 mt-3 -mb-1 text-[1.125rem] font-bold What you'll do /h4

ul class= [li_ ]:mb-0 [li_ ]:mt-1 [li_ ]:gap-1 [ :not(:last-child)_ul]:pb-1 [ :not(:last-child)_ol]:pb-1 list-disc flex flex-col gap-1 pl-8 mb-3 print:block print:space-y-1

li class= font-claude-response-body whitespace-normal break-words pl-2 strong Design and deliver production-grade agents. /strong 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. /li

li class= font-claude-response-body whitespace-normal break-words pl-2 strong Own the agent work; support the whole product. /strong 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. /li

li class= font-claude-response-body whitespace-normal break-words pl-2 strong Build agents only Honeycomb can build. /strong 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. /li

li class= font-claude-response-body whitespace-normal break-words pl-2 strong Extend the surface, and decide what's next. /strong 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. /li

li class= font-claude-response-body whitespace-normal break-words pl-2 strong Define what good means for agents here. /strong Set the bar: measurable against real evals, maintainable, and honest about their limits. /li

/ul

h4 class= text-text-100 mt-2 -mb-1 text-base font-bold Example projects /h4

ul class= [li_ ]:mb-0 [li_ ]:mt-1 [li_ ]:gap-1 [ :not(:last-child)_ul]:pb-1 [ :not(:last-child)_ol]:pb-1 list-disc flex flex-col gap-1 pl-8 mb-3 print:block print:space-y-1

li class= font-claude-response-body whitespace-normal break-words pl-2 strong Multiple agents collaborating on one shared Canvas investigation /strong each claiming a hypothesis, publishing findings, and narrowing the search space for the others so it resolves faster (blog). /li

li class= font-claude-response-body whitespace-normal break-words pl-2 strong Auto-investigation the moment an SLO burn alert fires /strong the agent forms hypotheses and prepares visualizations before a human looks, cutting mean-time-to-insight for on-call (o11ycon 2026). /li

li class= font-claude-response-body whitespace-normal break-words pl-2 strong Skills that encode a team's domain expertise /strong e.g. Kubernetes thresholds so agents and human colleagues can lean on them (o11ycon 2026). /li

/ul

h4 class= text-text-100 mt-3 -mb-1 text-[1.125rem] font-bold What you'll bring: /h4

ul class= [li_ ]:mb-0 [li_ ]:mt-1 [li_ ]:gap-1 [ :not(:last-child)_ul]:pb-1 [ :not(:last-child)_ol]:pb-1 list-disc flex flex-col gap-1 pl-8 mb-3 print:block print:space-y-1

li class= font-claude-response-body whitespace-normal break-words pl-2 strong AI and agent engineering experience. /strong 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. /li

li class= font-claude-response-body whitespace-normal break-words pl-2 strong End-to-end ownership. /strong 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. /li

li class= font-claude-response-body whitespace-normal break-words pl-2 strong Current judgment, not just past experience. /strong 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. /li

li class= font-claude-response-body whitespace-normal break-words pl-2 strong Agent architecture depth. /strong You understand how a fast, high-cardinality data store changes what an agent can reason about, and how to design for that. /li

li class= font-claude-response-body whitespace-normal break-words pl-2 strong Product judgment. /strong 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. /li

/ul

h4 class= text-text-100 mt-2 -mb-1 text-base font-bold Even better /h4

ul class= [li_ ]:mb-0 [li_ ]:mt-1 [li_ ]:gap-1 [ :not(:last-child)_ul]:pb-1 [ :not(:last-child)_ol]:pb-1 list-disc flex flex-col gap-1 pl-8 mb-3 print:block print:space-y-1

li class= font-claude-response-body whitespace-normal break-words pl-2 strong Observability or developer-tools background. /strong Engineers are your users; you'll ramp faster with fluency in that world, and the work is better. /li

li class= font-claude-response-body whitespace-normal break-words pl-2 strong Familiarity with eval frameworks, agent tooling, RAG, and prompt engineering. /strong /li

/ul div class= content-pay-transparency div class= pay-input div class= title Base Salary based on level of experience /div div class= pay-range span $183,340 /span span class= divider /span span $206,000 USD /span /div /div /div div class= content-conclusion div

p strong What you'll get when you join the Hive: /strong /p

ul

li A stake in our success - generous equity with employee-friendly stock program /li

li It’s not about how strong of a negotiator you are - our pay is based on transparent levels relative to experience /li

li Time to recharge with unlimited PTO /li

li A distributed-first mindset and culture (really!) /li

li Home office, co-working, and internet stipend /li

li data-stringify-indent= 0 data-stringify-border= 1 Full benefits coverage for employees, with additional coverage available for dependents /li

li Up to 16 weeks of paid parental leave, regardless of path to parenthood /li

li Annual development allowance /li

li And much more... /li

/ul

/div

div /div

div strong Please note we cannot currently sponsor or support visa transfers at this time. /strong Additionally, in compliance with applicable law, all persons hired will be required to verify identity and eligibility to work. /div

div /div

div /div

div strong Phishing and Recruitment Scam Warning: /strong /div

div We take your security seriously. Please be aware that recruitment scams are increasingly common and scammers may create email addresses or websites to impersonate Honeycomb employees. To help protect you: /div

div

ul

li All communications will come from an strong @honeycomb.io /strong email address

ul

li We occasionally work with external recruiting agencies. These partners will use legitimate business email addresses— strong data-start= 512 data-end= 559 never personal accounts like Gmail or Yahoo /strong . /li

/ul

/li

li Our recruiting process will strong data-start= 592 data-end= 601 never /strong ask you to provide financial or sensitive personal information, including but not limited to:

ul

li Social security or tax identification numbers /li

li Credit card numbers /li

li Bank account information /li

/ul

/li

/ul

p /p

/div

div strong Diversity Accommodations: /strong /div

div We're committed to building a diverse, inclusive, and equitable workplace—where 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. /div

div /div

div 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. /div

div /div

div As an equal opportunity employer our hiring process is designed to put you at ease and help you show your best work. If there’s anything we can do to improve your experience, we’re always open to feedback. /div

div /div

div /div

div strong Privacy Notice: /strong /div

div 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. /div

div /div

div For more information regarding our privacy practices please see the a href= https://www.honeycomb.io/privacy target= _blank Honeycomb Privacy Notice /a . /div

div /div

div If you do not want us to retain your information, or want us to update it, please contact a href= mailto:[email protected] target= _blank [email protected] /a . Please note, however, that we may retain some information if required by law or as necessary to protect ourselves from legal claims. /div /div