About the Role
Join a small team building AI agents and open-source tools for improving software instrumentation and telemetry. You will develop reliable coding-agent workflows that help engineering teams find and fix instrumentation issues across their codebases.
What You'll Do
Build features from specification through production, including GitLab support and workflows that turn telemetry findings into code fixes across repositories.
Improve agent-run reliability with structured outputs, retries, long-running sandbox jobs, and consistent findings across runs.
Develop evaluations to measure how prompt and model changes affect agent quality and cost.
Build the context agents need to review and safely change Go, Java, Kotlin, TypeScript, Python, and .NET code.
Maintain open-source agent skills, keep them current with OpenTelemetry releases, review contributions, and evaluate their impact.
Work with customer engineers and the Customer Success team when delivery requires it.
What We're Looking For
At least 5 years of software engineering experience and strong proficiency in TypeScript.
Comfort reading and safely changing code in Go, Java, Kotlin, Python, and .NET.
Experience measuring language model quality with evaluations, golden sets, or production signals.
Experience building with APIs, webhooks, durable workflows, and Postgres.
Ability to communicate through design documents, pull request descriptions, and clear written summaries in an async-first environment.
Open-source maintenance, OpenTelemetry instrumentation, or experience building agent skills, plugins, or MCP servers is valuable.
Experience with GitHub App or GitLab integrations, sandboxed code execution, Cloudflare Workers, or Bun is also useful.
Location
Fully remote. Primary location: Argentina.