Staff AI Engineer (AI)

TL;DR

Staff AI Engineer (Python/LLMs): Designing and scaling core autonomous AI infrastructure and the central orchestrator "Maestro" with an accent on agentic systems, RAG pipelines, and LLMOps. Focus on evolving a WhatsApp-based platform into a multi-agent enterprise system and automating complex tasks across payments and fraud.

Location: Remote (US), with hybrid options available in Miami and Mexico City

Company

Financial ecosystem for Latin immigrants in the US, revolutionizing remittances via AI-powered WhatsApp chatbots.

What you will do

• Architect and maintain "Maestro," the central AI orchestrator and its connected execution agents.
• Lead the integration of AI agents into product and operational infrastructure using Docker and Kubernetes.
• Establish production-grade LLMOps, including monitoring, tracing, and logging for agentic workflows.
• Design automated evaluation pipelines ("evals-as-code") to ensure agent safety and reliability.
• Optimize RAG pipelines, prompt compression, and model routing to balance inference costs with performance.
• Define operational best practices for AI deployment and asynchronous programming.

Requirements

• 8+ years of software engineering experience with a focus on infrastructure and systems development.
• 2+ years of experience deploying production-grade AI applications using LLMs.
• Exceptional mastery of Python and deep knowledge of System Architecture.
• Proven experience with RAG, tool-calling, vector databases, and agentic frameworks.
• Must be based in the US to be eligible for US-based benefits.

Nice to have

• Hands-on experience with Open CLAW, Hermes, or advanced open-source AI Agent frameworks.

Culture & Benefits

• Competitive salary, initial stock options, and annual performance bonuses.
• Comprehensive health, dental, and vision plans.
• 401(k) with employer match.
• Unlimited PTO and paid parental leave.
• Remote work environment with optional hybrid setups in Miami and Mexico City.