freehire launches on Product Hunt on 26 August.

Follow →

Sr Backend Engineer - AI

Summary

Build AI-powered observability tools: an AI teammate (Noz), MCP server for LLM agents, and LLM/GenAI observability using Go and async Python.

Role Description

We're looking for a Sr Backend Engineer for Nerve team, our AI pod. Nerve team builds the AI layer of SigNoz: Noz (observability AI teammate inside SigNoz), the SigNoz MCP server, AI SRE, and LLM/GenAI observability.

What you'll work on:

  • Noz, AI teammate: agent orchestration, tool execution, and the APIs that stream results back into the product
  • SigNoz MCP server that exposes observability data to LLM agents, so any agent can query a user's logs, metrics, and traces
  • The hard parts of agent backends: long-running execution, security, streaming over SSE, tool calling, and session state across DBs
  • LLM/GenAI observability, so teams (including us) can monitor their own AI apps with OpenTelemetry

Qualifications

  • 5-8 years building backend systems in production.
  • Strong with Go (concurrency, channels, performance) and with async Python (FastAPI, Pydantic, asyncio).
  • Comfortable designing APIs and data models.
  • Experience building and shipping LLM features in production: agents, tool or function calling, evals, MCP, context and prompt engineering.
  • Ability to drive initiatives end-to-end: from problem discovery → design → implementation → rollout.
  • Comfortable working in a high-ownership, fast-moving, remote-first environment.
  • Strong communication skills, can write clear tech docs and explain trade-offs.

Requirements

  • Experience building distributed systems while writing clean and scalable code.

Nice-to-haves

  • Past experience in AI or platform teams of series B+ startups.
  • Experience in observability (monitoring / logging / tracing).
  • Familiarity with OpenTelemetry and/or ClickHouse, Kafka, Kubernetes, etc.
  • Loves open source, ideally with prior contributions to OSS projects (any size).

Benefits

  • You'll help define agent-native observability, a new category, not maintain a mature dashboard product.
  • Work on a globally used open-source project that engineers actually love.
  • Collaborate with high-caliber team who just can't stop shipping.
  • Remote-first, async-friendly culture.
  • Opportunity to help define the future of open-source observability.