Sr Backend Engineer - AI

Role overview

Build backend systems for AI-powered developer observability, including an AI teammate, agent integrations, and tools for querying application telemetry. The work spans agent orchestration and LLM observability, with an emphasis on making unpredictable AI behavior dependable in production.

Responsibilities

- Develop backend capabilities for agent orchestration, tool calling, streaming over server-sent events, and session state. - Build an MCP server that lets LLM agents query logs, metrics, and traces, and create alerts and dashboards. - Develop observability for generative AI applications using OpenTelemetry. - Take initiatives from problem discovery through design, implementation, and rollout. - Document decisions clearly and explain technical trade-offs to teammates.

Requirements

- 5–8 years of experience building production backend systems at product-focused companies. - Strong Go skills, including concurrency, channels, and performance considerations. - Strong asynchronous Python skills, including FastAPI, Pydantic, and asyncio. - Experience designing APIs and data models. - Ownership in a fast-moving, remote-first environment, with the ability to deliver work from initial investigation through release. - Curiosity about LLMs and agents, plus the engineering judgment to make non-deterministic systems more reliable.

Nice to have

- Production experience with LLM features such as agents, tool or function calling, evaluations, MCP, or prompt and context engineering. - Familiarity with OpenTelemetry, ClickHouse, Kafka, or Kubernetes. - Open-source contributions.

Benefits and work setup

- Remote-first, async-friendly work. - Opportunity to shape emerging approaches to AI-focused observability and contribute in the open.