You and the process

With a person
Anna, in-house recruiter
9 years hiring engineers
30 minutes with a real recruiter
They read your CV with you, on a call, and say where the offers are being lost.
Didn’t find what you were looking for? Tell us what to build
Honeycomb.io

Senior Software Engineer II - Agentic Intelligence

  • Remote
  • 6+ years

Salary

Not stated

Similar roles pay $115K - 185K a year · our estimate

AI summary

For members

The whole posting in a few lines. Sign up to read it here and on every role you open.

Sign Up to Read

Description

The company runs a service for observability, the practice of understanding systems from their live telemetry, and works with customers such as HelloFresh, Slack, LaunchDarkly and Vanguard across several industries.

The company closed a Series D round, has grown past 200 staff, and was named to Forbes' America's Best Startups list for 2022 and 2023.

The team builds AI agents that investigate, reason about and act on live observability data inside the company's agentic workspace, where engineers go to understand their systems. The team has already shipped that workspace, the MCP server and the agent and skills features, and now aims to extend them with new agents, memory, spatial awareness and faster performance on the Bedrock loop.

The team is small, collaborative and distributed, and it values humble peers who share strong opinions.

Responsibilities

  • Design and ship production-grade agents that investigate, reason about and act on live observability data in the workspace, including mid-incident, when engineers need to trust them most.
  • Take an agent from a rough first version to one that performs under real production traffic.
  • Own the agent work end to end: scope, build, ship and maintain agents, along with the evals that show whether they improved or only changed.
  • Work on some fullstack development alongside the agent work.
  • Build agents that rely on the company's high-cardinality data store, which returns queries in seconds, to reason over signals a conventional backend cannot serve at that detail, such as correlating across services, drilling into a single trace, or comparing behaviour before and after a deploy.
  • Extend the product into the workspace, the MCP server, skills, memory, spatial awareness and the Bedrock loop, and decide what comes next, backing the case with working code.
  • Set the standard for agent quality: measurable against real evals, maintainable and clear about limitations.
  • Example work: several agents sharing one investigation, each claiming a hypothesis, publishing findings and narrowing the search so the others resolve it faster.
  • Example work: automatic investigation when an SLO burn alert fires, where the agent forms hypotheses and prepares visualisations before an on-call engineer looks.
  • Example work: skills that capture a team's domain knowledge, such as Kubernetes thresholds, so agents and colleagues can both use them.

Requirements

  • Experience building and shipping LLM-based systems that real users relied on in production, not demos or research-only fine-tuning.
  • Knowledge of where agent systems fail and how to design around those failures.
  • Full ownership of work from prototype to production, without depending on someone else to do the durable engineering.
  • Current views, based on the last six to twelve months, on what has changed in agent design and how you would build differently today.
  • An understanding of how a fast, high-cardinality data store changes what an agent can reason about, and how to design for it.
  • Product judgment to see what the agent layer should do next and argue for it with a prototype rather than a slide deck.
  • Even better: background in observability or developer tools, since engineers are the users and fluency there helps you ramp faster.
  • Even better: familiarity with eval frameworks, agent tooling, RAG and prompt engineering.

Conditions

Base salary is set by level of experience, between $250,000 and $280,000 CAD.

The role is fully remote. The company cares about how you work and fit its culture and processes, and gives trust, autonomy and accountability from day one.

The company cannot currently sponsor visas or support visa transfers. All hires must verify their identity and eligibility to work.

The company will only contact you from an company's site address and will never ask for financial details or sensitive personal information during recruiting.

Benefits

  • Equity through an employee-friendly stock programme.
  • Pay set on transparent levels tied to experience, not negotiation.
  • Unlimited paid time off.
  • A distributed-first culture.
  • A stipend for home office, co-working and internet.
  • Full benefits for employees, with extra coverage available for dependants.
  • Up to 16 weeks of paid parental leave, whatever path to parenthood you take.
  • An annual development allowance.
  • Further perks beyond these.

Where you’d work

Fully remote

You can work from

  • Canada

No visa sponsorship

About the company

Honeycomb.io

  • Industry: SaaS

12 of their 12 open roles are remote

Your chances

Worth a look before you spend an evening tailoring a CV for it.

  • 19 checks run
  • 1 red flag

Still hiring?

13 checks

1 red flag

How crowded?

6 checks

No red flags

Fits Me

How well does this role fit you?

Answer a few questions or drop your CV, and every role gets a fit score with the reasons, this one first.

  • Your field
  • Level
  • Stack
  • Work model
  • Salary floor
  • Must-haves
Details14 facts · Role, Location, Compensation, Employment, Company
Tech stack
  • Kubernetes
  • LLMs
  • RAG
Seniority
Senior
Type
Full-time
Equity
Equity offered
Industry
SaaS
Specialty
Backend
Show 8 more factsShow less

Role

Category
Development
Specialty
Backend
Seniority
Senior
Experience
6+ years
Tech stack
  • Kubernetes
  • LLMs
  • RAG

Location

Work model
Remote
Region
Canada
Remote from
  • Canada
Visa sponsorship
Not sponsored

Compensation

Salary
Salary by agreement
Pay period
Annual
Equity
Equity offered

Employment

Type
Full-time

Company

Industry
SaaS

Something wrong with this vacancy?

Similar vacancies

Share this vacancy

What's wrong with it?

The employer never sees who reported.

Reason