Senior AI Engineer - Production Reliability & Agents (Remote)

Aimlroles; United States; Remote; USD 56,000 - 67,000; Full time

Job summary

Aimlroles is seeking a Senior or Staff Engineer to own production reliability for AI agents and related workflows. You will manage multiple AI agents, ensure robust monitoring, and own the end-to-end reliability of voice, reviews, and reporting components. This fully remote role targets candidates in Canada, Argentina, Brazil, or the United Kingdom who can operate on U.S.

Eastern Time. You will work as an independent contractor, lead incident response, and shape tooling for evaluation and

Qualifications

• 7+ years building and operating production systems with on-call ownership.
• Hands-on LLM applications in production: tool calling, prompt and context debugging, evals.
• Daily, disciplined use of AI coding tools (Claude Code, Codex, Cursor) with 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.

Responsibilities

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

Skills

Production systems

LLM in production

Python

TypeScript

MongoDB/PostgreSQL

LLM tool calls / debugging

Tracing & monitoring

Tools

Langfuse or similar

Claude Code

Codex

Cursor

Job description

Aimlroles is seeking a Senior or Staff Engineer to own production reliability for AI agents and related workflows. You will manage multiple AI agents, ensure robust monitoring, and own the end-to-end reliability of voice, reviews, and reporting components. This fully remote role targets candidates in Canada, Argentina, Brazil, or the United Kingdom who can operate on U.S.

Eastern Time. You will work as an independent contractor, lead incident response, and shape tooling for evaluation and