NodJobsNodJobs

Senior Software Engineer II - Agentic Intelligence

Honeycomb Β· Remote - United States

πŸ‡ΊπŸ‡Έ Remote (US)Senior$183,340 – $206,000/yr1d ago

At a glance

Where
Remote β€” open to applicants in the United States
Pay
$183,340 – $206,000/yr β€” as listed by Honeycomb
Level
Senior
Visa
The company cannot currently sponsor or support visa transfers.
Posted
November 17, 2026
Last confirmed open
1h ago
At Honeycomb
7 open remote roles β€” mostly Software Development (4), AI & Machine Learning (1), Marketing (1). Pay is listed on 7 of them ($125,000 – $265,000/yr).
How to apply
Directly on Honeycomb's own site β€” no NodJobs account needed.

About the role

This role builds and maintains AI agents that investigate and act on live observability data inside Honeycomb's Canvas workspace, plus the Canvas, MCP server and Canvas Skills surfaces, with some fullstack work. It suits a senior engineer with hands-on experience shipping LLM-based agent systems to production and owning work from prototype to production.

What you'll do

  • Design and deliver production-grade agents that investigate, reason, and act on live observability data inside Canvas, trustworthy to engineers mid-incident.
  • Take agents from rough first version to production-ready under production traffic.
  • Own agent scope, build, shipping and maintenance, including evals that measure whether agents improve.
  • Build fullstack features alongside agent work.
  • Build agents that use high-cardinality queries over signal across services, single traces, and before/after deploy comparisons.
  • Extend Canvas, the MCP server, and Canvas Skills, including memory, spatial awareness, and a faster Bedrock loop.
  • Propose next directions for the agent layer and make the case with working code.
  • Define measurable, maintainable quality standards for agents, including evals and stated limitations.
  • Build example agents such as multi-agent collaboration on shared Canvas investigations and auto-investigation when SLO burn alerts fire.
  • Encode team domain expertise into skills, such as Kubernetes thresholds, for agents and human colleagues to use.
  • Distinguish hype from signal in the agent field.

What you'll need

  • AI and agent engineering experience shipping LLM-based systems relied on in production.
  • End-to-end ownership, taking work from rough prototype to production-grade without a handoff.
  • Current judgment on how agent design has shifted in the last six to twelve months.
  • Agent architecture depth, including how a fast high-cardinality data store changes what an agent can reason about.
  • Product judgment to identify next steps for the agent layer and make the case with a prototype.

Nice to have

  • Observability or developer-tools background.
  • Familiarity with eval frameworks, agent tooling, RAG, and prompt engineering.

Benefits listed by Honeycomb

  • Equity through an employee-friendly stock program
  • Unlimited PTO
  • 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

Tools & skills mentioned

CanvasMCP serverBedrockLLM

Summarized by NodJobs from Honeycomb's posting. Read the full posting on Honeycomb's site β†’

NodJobs is free for job seekers β€” we never charge to apply, and this role takes you straight to the company's own application.

Similar live jobs