Join a dynamic team as a Software Engineer, where you'll build impactful applications and systems in AI-powered healthcare, taking ownership of your projects.
Senior Software Engineer I - Agent Observability
📜 Description
- Deliver AI observability capabilities from ingestion through in-product visualizations.
- Contribute to the data model and infrastructure for observing agents and their ecosystems.
- Build systems that surface AI signals, including cost, token usage, errors, and anomalies.
- Partner with product managers and designers to create intuitive features and useful workflows.
- Share insights into AI system behavior across conversations and workloads.
- Iterate through experimentation and fast feedback loops, sharing successes and failures.
🛠️ Requirements
- 3+ years of software engineering experience.
- Experience shipping customer-facing features at a SaaS company, beyond internal tooling.
- Full-stack range, with proficiency in backend development (Go and/or Python) and frontend development (TypeScript and React).
- A track record of working with product managers and designers.
- Regular, hands-on use of AI tools in your day-to-day engineering work.
- Experience being on call. You'd join our rotation after about 90 days.
- A track record of navigating ambiguity in a fast-moving field where requirements shift and experimentation is a core part of the job.
- Bonus: Experience building LLM or agent-powered features in production.
- Bonus: Hands-on experience with observability tooling, such as OpenTelemetry.
✨ Benefits
- A stake in our success - generous equity with employee-friendly stock program
- It’s 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
- 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
Full job description
Little more about the team:
The team builds observability for AI in Honeycomb. We help customers see what their agents are doing, what those agents cost, and where errors happen. We also give them insight into individual conversations so they can debug them. We're bringing LLM and agent observability together, and we own both the data foundation and the product experiences built on top of it. You'll work in a small, cross-functional group of engineers with a dedicated product manager and designer, shipping features customers use in production. If you want to define how people understand and debug AI systems, this is the team for you.
What you’ll do in the role:
- Deliver AI observability capabilities end to end, from ingestion to in-product visualizations.
- Contribute to the data model and infrastructure that let us observe agents and their ecosystems across the Honeycomb product.
- Build systems that analyze and surface AI-specific signals, such as cost, token usage, errors, and anomalies.
- Collaborate with product and design partners to make sure what we build is usable, intuitive, and unlocks meaningful user workflows.
- Share what you learn about exploring and understanding AI system behavior across conversations and workloads.
- Iterate through fast feedback loops and experimentation, and share both wins and failures.
What you’ll bring to the role:
- 3+ years of software engineering experience.
- Experience shipping customer-facing features at a SaaS company, beyond internal tooling.
- Full-stack range, with proficiency in backend development (Go and/or Python) and frontend development (TypeScript and React).
- A track record of working with product managers and designers.
- Regular, hands-on use of AI tools in your day-to-day engineering work.
- Experience being on call. You'd join our rotation after about 90 days.
- A track record of navigating ambiguity in a fast-moving field where requirements shift and experimentation is a core part of the job.
- Bonus: Experience building LLM or agent-powered features in production.
- Bonus: Hands-on experience with observability tooling, such as OpenTelemetry.
What you'll get when you join the Hive:
- A stake in our success - generous equity with employee-friendly stock program
- It’s 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 allowance
- 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 addresses—never 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
Similar jobs
Search more Software Engineer jobsSystems Engineer - Behavior Verification
Define and validate scenario-based test sets for autonomous driving behavior, investigate failures and simulation gaps, and determine whether software releases meet safety and performance criteria.
Provides field-based engineering support to mining operations, translating mine plans into safe and efficient execution while optimizing production, monitoring performance, and identifying operational improvements.
Forward Deployed Engineer, Frontier Engineering
Build and deploy production-grade AI agents and applications for strategic customers, owning the lifecycle from prototype to production while measuring and improving quality, reliability, and scale.
Build and maintain software, tools, and infrastructure for cybersecurity research, AI risk evaluations, and red teaming, partnering with researchers to turn experimental workflows into reliable systems.
