AI Agent Engineer

Staging Meetgail; Miami (FL); Hybrid; USD 180,000 - 250,000; Full time

Job summary

Staging Meetgail is seeking a production AI systems engineer to design, implement, and maintain LLM-powered workflows in a fast‑moving startup setting. You will build production agents, call tooling, retrieval systems, and structured outputs, focusing on reliability and cost efficiency.

You should be proficient in Python, APIs, and cloud infrastructure, with hands-on experience in building with LLMs and driving real-world impact in customer interactions.

Qualifications

• Shipping production systems with strong software engineering fundamentals.
• Hands-on experience with Python, APIs, and cloud infrastructure.
• Experience building with LLMs, including prompting, tool calling, retrieval, and structured outputs.
• Experience debugging production systems, improving reliability and observability.
• Ability to translate business problems into technical solutions.
• Clear communication across technical and non-technical teams.
• Ownership and ability to move quickly in a startup.

Responsibilities

• Build, deploy, and maintain production AI agents and workflows.
• Design tool-calling pipelines, retrieval systems, structured outputs.
• Improve agent reliability, observability, and cost efficiency in production.
• Debug and resolve issues in live AI systems handling real customer interactions.
• Collaborate with product and engineering to translate business needs into agent capabilities.
• Evaluate and iterate on agent performance using structured evals and real-world feedback.

Skills

Software engineering

Python

LLMs

Production systems

Observability

Cost efficiency

Communication

Startup experience

Tools

APIs

Cloud infrastructure

Retrieval systems

Tool calling

Job description

Miami, FL / Bay Area, CA $180,000 – $250,000 base · equity included

About the role

We need someone who thinks in production systems — obsessed with building AI agents that actually do real work, in real workflows, with real stakes. This is not a research or prototype environment. Our agents have already helped collect $235M, powered 150M+ calls, and handled 100M+ texts. We need someone who wants to make them sharper, faster, and more reliable.

The work.

• Build, deploy, and maintain production AI agents and LLM-powered workflows
• Design and implement tool-calling pipelines, retrieval systems, and structured output logic
• Improve agent reliability, observability, and cost efficiency in production
• Debug and resolve issues in live AI systems handling real customer interactions
• Collaborate with product and engineering to translate business needs into agent capabilities
• Evaluate and iterate on agent performance using structured evals and real-world feedback

The profile.

• Strong software engineering fundamentals and experience shipping production systems
• Proficiency in Python and comfort with APIs, backend services, and cloud infrastructure
• Hands‑on experience building with LLMs — prompting, tool calling, retrieval, structured outputs, and evals
• Experience debugging production systems and improving reliability, observability, and cost efficiency
• Strong product instincts and the ability to translate ambiguous business problems into practical technical solutions
• Clear communicator who works well across technical and non-technical teams
• High ownership and comfort moving quickly in a startup environment