AI Engineer

❤️ About Poppy AI; Canada; Remoto; CAD 78.000 - 94.000; Tempo pieno

Descrizione del lavoro

Poppy AI is seeking a Senior/Staff Engineer to own production reliability for AI agents and related systems. You will lead multiple AI coding agents, ensure robust monitoring, and maintain a clean, scalable codebase while delivering fast improvements.

You will design and implement tooling for tracing, alerting, and failure replay, and work across scheduling, telephony, and marketing integrations. This is a fully remote, contract role aligned to U.S. ET business hours.

Competenze

• 7+ years building and operating production systems.
• Experience with LLM apps in production and tool calling.
• Daily, disciplined use of AI coding tools (Claude Code, Codex, Cursor), including running several agents in parallel.
• Experience with messy third‑party integrations (scheduling systems, telephony, marketing and ad platforms).

Mansioni

• Production reliability and incident response across our AI agents and integrations.
• Debugging and evaluation tooling for LLM agents (prompt, context and tool-call tracing; regression evals; failure replay).
• A real-time availability viewer and configurator: make the voice agent offerings visible and configurable per office needs.
• Helping finish and harden the Marketing Report and the Website Builder.

Conoscenze

Python

TypeScript

LLM in production

Tool calling

Prompt debugging

Context debugging

Eval frameworks

MongoDB

PostgreSQL

Parallel agents

Strumenti

Langfuse

Claude Code

Codex

Cursor

MongoDB

PostgreSQL

Descrizione del lavoro

Senior / Staff Engineer: AI Agents & Production Reliability

Job Description

Location: Remote, Canada, Argentina, Brazil and the United Kingdom

Working hours: Must work U.S. Eastern Time (ET) business hours

Compensation: USD 5,000 to 6,000 per month (full-time), depending on experience

Schedule: Full-Time

Contract: Full-Time Independent Contractor

We are is an all-in-one AI marketing platform for dental practices. Our AI tools and agents improve a practice's online visibility (search, reviews, reputation, website) and work around the clock to bring in more patients, from an AI voice receptionist that books directly into the practice's schedule to automated review requests and marketing reporting. We're live with dozens of offices and growing fast.

WHO WE'RE LOOKING FOR

• You run multiple AI agents, well. You direct several AI coding agents in parallel, review what they produce critically, and keep a codebase clean while moving fast. You also own our production agents (voice, reviews, reporting) as systems, not demos.
• You know where AI helps and where it doesn't. You decide deliberately when to delegate to an AI agent and when to write the code yourself: tricky concurrency, scheduling logic, security, anything where being subtly wrong is expensive.
• You debug fast and systematically. You form a hypothesis, check the logs and traces, and find the root cause, whether it's in our code, a vendor API, or the model's prompt and context.
• You build the monitoring that's missing. If you can't see it, you instrument it: tracing across every call and agent action, alerts that fire on real failures, dashboards people actually use.
• You can pinpoint where an LLM went wrong: which prompt section, which tool call, which piece of context. Then you prove the fix with evaluations and replays of real failures.
• You own outcomes. You don't wait for tickets; you find what's broken, fix it, and make sure it stays fixed.

WHAT YOU'LL WORK ON

• Production reliability and incident response across our AI agents and integrations.
• Debugging and evaluation tooling for LLM agents (prompt, context and tool-call tracing; regression evals; failure replay).
• A real-time availability viewer and configurator: every office schedules differently, so make it visible and configurable exactly what the voice agent will offer, and why.
• Helping finish and harden the Marketing Report and the Website Builder.

WHAT YOU NEED

• 7+ years building and operating production systems, with real on-call and incident ownership.
• Hands‑on LLM applications in production: tool calling, prompt and context debugging, evals (Langfuse or similar).
• Daily, disciplined use of AI coding tools (Claude Code, Codex, Cursor), including running several agents in parallel.
• Strong Python and TypeScript; event‑driven services; MongoDB or Postgres.
• Experience with messy third‑party integrations (scheduling systems, telephony, marketing and ad platforms).
• Ability to work U.S. Eastern Time business hours.
• Based in Canada, Argentina, Brazil or the United Kingdom, and able to work as an independent contractor.

BONUS POINTS

• Scheduling or constraint systems.
• Marketing tech.
• HIPAA.
• Twilio or voice AI.

ENGAGEMENT DETAILS

• Full‑time independent contractor engagement (not employment); this role is open to candidates outside the U.S. only.
• Compensation: USD 5,000 to 6,000 per month (full-time), depending on experience.
• Fully remote, working U.S. Eastern Time hours.