21 hours ago

Senior Software Engineer II - Agentic Intelligence

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 8 hours agoStatus: Live

Job Summary

Build production-grade AI agents that investigate, reason, and act on live observability data inside Canvas. You’ll own agent and related full-stack development end-to-end, including evals to measure improvements, and extend Canvas capabilities such as memory and spatial awareness. Using Honeycomb’s fast, high-cardinality data store, you’ll ship agent experiences that outperform conventional observability backends and define what “good” means for agents via real evals.

Location: United States

Workplace: Remote

Employment Type: Full time

Job Function: Software Engineering

Seniority: Mid level

Key Responsibilities

•Design and deliver production-grade agents that investigate, reason, and act on live observability data in Canvas, including during mid-incident situations.
•Scope, build, ship, and maintain agents and evals to determine whether agents improve or change in meaningful ways.
•Leverage Honeycomb’s high-cardinality data store to build agents capable of cross-service correlation, trace drilling, and before/after deploy comparisons.
•Extend Canvas surface area, Canvas MCP server, and Canvas Skills (memory and spatial awareness), including improving Bedrock loop performance.
•Define “good” for agents using measurable real evals while keeping solutions maintainable and honest about limitations.

Pay and Benefits

Salary: USD 183,340 - 206,000

Perks:EquityPaid LeaveParental LeaveInternet StipendHome Office

Key Requirements

•Ship LLM-based systems relied on in production, not demos, and know where agent systems fail and how to design around it.
•Demonstrate end-to-end ownership: take prototypes to production-grade without handoff queues.
•Bring current judgment on how agent design has shifted over the last 6–12 months and how that changes how you’d build today.
•Apply agent architecture depth, including how fast, high-cardinality data stores change what agents can reason about.
•Show product judgment by identifying what the agent layer should do next and backing it with working prototypes.

Skills:End-to-end ownershipProduct judgmentCurrent judgmentTrustworthiness in high-pressure situationsAgent system design

Languages:English

Tech Stack:AI agentsLLMsRAGPrompt engineeringEval frameworksMCP serverBedrock loopCanvasObservabilityHigh-cardinality dataKubernetes

Eligibility

Work Authorization:Authorization required. Sponsorship not provided.

Company Brief

honeycomb.io

Provides a cloud-based observability platform that helps engineering teams debug, explore, and understand production systems by ingesting high-cardinality event data for fast querying and real-time analysis.

Industry: Developer Tools

Company Size: Medium (51 to 250 employees)

Growth: Growth Stage Startup

Headquarters: San Francisco, United States

Founded: 2016

Website LinkedIn

Loading job details...

Preparing the role view and application actions.

honeycomb.io

21 hours ago

Senior Software Engineer II - Agentic Intelligence

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 8 hours agoStatus: Live

Job Summary

Location: United States

Workplace: Remote

Employment Type: Full time

Job Function: Software Engineering

Seniority: Mid level

Key Responsibilities

•Design and deliver production-grade agents that investigate, reason, and act on live observability data in Canvas, including during mid-incident situations.
•Scope, build, ship, and maintain agents and evals to determine whether agents improve or change in meaningful ways.
•Leverage Honeycomb’s high-cardinality data store to build agents capable of cross-service correlation, trace drilling, and before/after deploy comparisons.
•Extend Canvas surface area, Canvas MCP server, and Canvas Skills (memory and spatial awareness), including improving Bedrock loop performance.
•Define “good” for agents using measurable real evals while keeping solutions maintainable and honest about limitations.

Pay and Benefits

Salary: USD 183,340 - 206,000

Perks:EquityPaid LeaveParental LeaveInternet StipendHome Office

Key Requirements

•Ship LLM-based systems relied on in production, not demos, and know where agent systems fail and how to design around it.
•Demonstrate end-to-end ownership: take prototypes to production-grade without handoff queues.
•Bring current judgment on how agent design has shifted over the last 6–12 months and how that changes how you’d build today.
•Apply agent architecture depth, including how fast, high-cardinality data stores change what agents can reason about.
•Show product judgment by identifying what the agent layer should do next and backing it with working prototypes.

Skills:End-to-end ownershipProduct judgmentCurrent judgmentTrustworthiness in high-pressure situationsAgent system design

Languages:English

Tech Stack:AI agentsLLMsRAGPrompt engineeringEval frameworksMCP serverBedrock loopCanvasObservabilityHigh-cardinality dataKubernetes

Eligibility

Work Authorization:Authorization required. Sponsorship not provided.

Company Brief

honeycomb.io

Industry: Developer Tools

Company Size: Medium (51 to 250 employees)

Growth: Growth Stage Startup

Headquarters: San Francisco, United States

Founded: 2016

Website LinkedIn