Remote job
Senior Software Engineer II - LLM Observability
Job details
About this role
Role overview Build observability features that help customers understand and troubleshoot AI agents in production. This full-stack role spans the data foundation—from ingestion and modeling to product experiences that reveal how agents behave, what they cost, and where they fail. You’ll work with a small cross-functional team and ship capabilities directly to customers.
Responsibilities - Develop AI observability features across the pipeline, from data ingestion through in-product visualizations. - Design and evolve data models and infrastructure for observing agents and their surrounding systems. - Build ways to analyze and surface signals such as token use, cost, errors, and unusual behavior. - Partner with product and design to shape clear, useful workflows for customers. - Help customers and colleagues learn effective ways to explore agent behavior across conversations and workloads. - Use rapid feedback and experimentation to improve features, sharing lessons from both successful and unsuccessful approaches.
Requirements - Significant software engineering experience, including ownership of features from idea through delivery. - Experience shipping customer-facing SaaS product features. - Full-stack capability, with backend experience in Go and/or Python and frontend experience in TypeScript and React. - Strong collaboration with product managers and designers. - Regular, hands-on use of AI tools in engineering work. - Experience participating in an on-call rotation; the role joins the rotation after roughly 90 days. - Comfort working through changing requirements and ambiguity in a fast-moving area.
Nice to have - Experience building production features powered by LLMs or agents. - Familiarity with observability tools such as OpenTelemetry.
Benefits and work setup - Fully distributed work model with trust and autonomy. - Salary range: CAD $250,000–$280,000, based on experience level. - Equity, unlimited paid time off, home office or coworking and internet support, employee benefits coverage, up to 16 weeks of paid parental leave, and an annual development allowance.