Production Management Engineer

Become the next Production Management Engineer who transforms cross-border finances. We invite you to build with us a banking product that moves thousands of dollars around the world every second. At Global66, your work has a direct impact: improving the quality of life for people and companies through advanced technological financial products and services.

Our Tribune and Our Culture

Global66 Tribune: We are a diverse Tribune of over 350 partners in Chile, Peru, Colombia, and Argentina. We are united by a service that knows no borders and an undeniable passion for what we do. Here we recognize collective responsibility and celebrate every achievement with the same intensity as a sports victory.

At Global66, we are building a customer-centric global financial services ecosystem. Our philosophy is simple: "Start with the customer." We always ask ourselves what is best for the customer and develop the solution.

Your next challenges 🚀

The Global66 Production Management Engineer is in the "engine room" of Global66, the center where all the action happens. They must develop mechanisms to detect anomalies, and when they occur — perform an initial analysis. Both aspects are based on correctly applied Artificial Intelligence.

Their responsibilities include:

Operational Incident Management (Reactive)

• Monitoring events and incidents reported by automated systems or internal users.
• Preliminary diagnosis of incidents by querying databases, system logs, and checking services.
• Registration, classification, categorization, and prioritization of incidents based on their impact and urgency.
• Efficient coordination of involved parties (management, developers, operations, CX, vendors, and external parties).
• Escalation of complex incidents to specialized support teams or external vendors.
• Active tracking of open incidents and verifying in the production environment if the applied solution actually resolves the incident.
• Compliance with established SLAs and proper documentation of each incident and its resolution process.

Prevention and Early Detection

• Development and execution of processes aimed at preventing incidents (e.g., capacity and resource utilization monitoring).
• Development and execution of processes aimed at early detection (e.g., error monitoring in logs, monitoring incoming requests from CX or vendors, business rule monitoring, etc.).

Automation and AI applied to Incidents

• Identification of high-volume or repetitive processes in the incident management workflow that can be automated using AI.
• Design, creation, and iterative refinement of end-to-end workflows that combine AI agents with business logic, prioritizing direct impact on MTTD and MTTR.
• Adjustment of prompts, decision-making logic, and agent configurations according to observed results.
• Creation of rapidly deployable AI agents capable of monitoring, diagnosing, alerting, and coordinating solutions.
• Management of integrations between internal systems and automation tools (APIs, knowledge bases, Datadog, Slack, Jira, N8N, etc.).
• Conducting testing and validation before releasing changes to the production environment, and being the full owner of each implemented workflow, ensuring its stability, efficiency, and continuous improvement.
• Documenting architectures, design decisions, and maintenance procedures, as well as keeping the knowledge base used by agents up-to-date.

Communication and Coordination

• Periodically informing internal departments about the status of managed incidents.
• Carrying out communications with customers, vendors, or external partners when necessary.

Continuous Improvement

• Analysis of trends, patterns, and interactions in incidents to identify systemic weaknesses and opportunities for improvement or new use cases with AI.
• Participation in post-mortem analysis sessions for significant incidents.
• Collaboration with the Incident Manager and team in updating internal procedures and strengthening incident prevention and management processes.

Who are we looking for?

• You must be finishing your university studies in majors such as Systems Engineering or related fields.
• Availability for a 6-month internship with the possibility of transitioning to a full-time position.
• Possession of student insurance.