Build dependable LLM systems remotely across Canada, Argentina, Brazil, or the United Kingdom with prompt tracing and failure replay expertise. Work U.S. Eastern Time hours.

As a Senior or Staff Engineer, you will improve AI tools serving dental practices through disciplined debugging and evaluation. You will decide when agents should code and when careful implementation is required. Your focus includes observability, concurrency, scheduling logic, security, and vendor integrations.

Key Responsibilities:

- Investigate incidents across production agents and integrations
- Identify prompt, context, tool-call, and model failures
- Instrument every relevant agent action and service call
- Evaluate regressions using real failure replays
- Build the real-time availability viewer and configurator

Requirements:

- Seven-plus years building and operating production systems
- Hands-on production LLM application experience
- Daily use of Claude Code, Codex, or Cursor
- Robust Python, TypeScript, MongoDB or Postgres experience
- Residence in an eligible country and contractor status

Bring systematic LLM debugging, observability, and production engineering skills to reliable AI agents for dental practices.

📌 Staff LLM Production Systems Engineer (Canada)
🏢 ❤️ About Poppy AI
📍 Canada