Remote AI Engineer

HireLatam is a premier recruitment agency that places top Latin American talent in independent contractor roles in US companies. With a proven track record and a commitment to excellence, we’re your trusted partner in the pursuit of career success. Our extensive network, personalized approach, and supportive guidance ensure that you’re in the best hands to find your next job opportunity.

Job Title: Remote AI Engineer (100% Work From Home)

Location: Remote from Latin America

Position Type: Full-time

Salary: $6,500 USD/month

Schedule: Monday – Friday, 9:00 AM – 6:00 PM LATAM hours with lunch break.

About the Client

Our Client is a tech-forward platform company where AI agents serve as core operational infrastructure rather than ancillary features. Designing and deploying multi-agent systems directly on top of their core application, our client automates complex customer-facing and internal workflows—ranging from customer access support and user onboarding to WhatsApp conversational streams, real-time voice/call interactions, and business intelligence analytics. Operating with rigorous production standards, our client prioritizes system reliability, automated evaluation pipelines, low-latency streaming, and robust observability for high-volume customer interactions.

About the Role

Our Client is seeking a production-focused Senior AI Engineer to design, build, and operate multi-agent systems at scale. This is a hands-on execution role for a seasoned engineer who treats AI systems with the same engineering rigor as traditional mission-critical infrastructure. Reporting directly to engineering leadership, this professional will architect multi-agent handoffs, optimize low-latency streaming pipelines (including voice and WhatsApp channels), build automated evaluation frameworks, and instrument end-to-end observability across all live conversational agents.

Key Responsibilities

Multi-Agent System Architecture & Orchestration

• Designs and deploys multi-agent orchestration frameworks on top of existing product infrastructure, establishing clear agent roles, tool access permissions, memory structures, and handoff protocols.
• Builds low-latency, responsive streaming architectures that power real-time conversational agents across text, WhatsApp, and live voice/call pipelines.
• Integrates autonomous agents with internal APIs, databases, and business intelligence dashboards to execute complex, multi-step customer workflows seamlessly.

Evaluation, Testing & Quality Assurance

• Owns the end-to-end evaluation lifecycle, designing automated scoring pipelines, test datasets, and “LLM-as-judge” setups to prevent hallucinations, quality regressions, and drift.
• Implements robust safety guardrails and boundary constraints for autonomous agents making real-time decisions or holding live conversations with minimal human oversight.
• Debugs, troubleshoots, and refines non-deterministic agent outputs across live production environments to maintain high accuracy and customer satisfaction.

Observability, Security & Full Lifecycle Operations

• Instruments comprehensive observability suites, tracking structured logs, detailed agent execution traces, tool calls, token costs, latency distributions, and accuracy metrics.
• Manages the complete agent feature lifecycle—from prompt engineering and system design to API integration, unit testing, CI/CD deployment, and production monitoring.
• Collaborates closely with product and core software engineering teams to ensure clean, modular integration into the existing application codebase without service disruption.

Qualifications, Skills, and Key Competencies

Required Qualifications

• Production Multi-Agent Experience: Proven, hands-on background building and orchestrating multi-agent LLM architectures in live, user-facing production environments (not limited to prototypes, personal projects, or hackathons).
• Agent System Design Mastery: Deep understanding of agent design patterns, including role separation, coordination/handoff logic, function calling/tool usage, long/short-term memory management, and advanced RAG architectures.
• Streaming & Low-Latency Architecture: Demonstrated expertise in building low-latency, streaming data architectures for real-time responsiveness.
• Systematic Evaluation Frameworks: Practical experience establishing automated testing, regression detection pipelines, and quality scoring systems for…