Principal SRE – AI Agents Platform

Job not on LinkedIn

5 hours ago

Apply Now

Receive Emails with Similar Jobs

iFood

WebsiteLinkedInAll Job Openings

eCommerce • Food Delivery • Technology

iFood is a leading food delivery platform based in Brazil, connecting customers with a wide array of restaurants and food options. The company leverages cutting-edge technology and artificial intelligence to improve customer experience, streamline operations, and enhance delivery logistics. iFood fosters a diverse and inclusive work environment, focusing on sustainability and the positive impact of its services on the community.

5001 - 10000 employees

🛍️ eCommerce

📋 Description

• Lead the technical development and maintenance of the AI agents platform, ensuring agent reliability, scalability, and governance. • Design execution, deployment, telemetry, and monitoring patterns, contributing to critical architectural decisions and the platform's long-term vision. • Build automations and MLOps-oriented pipelines focused on observability, performance metrics, resilience, and efficient resource usage. • Define and monitor SLOs, SLIs, and protection mechanisms, providing clear communication of risk and impact to technical partners. • Evaluate vendors and technologies in the AI ecosystem, objectively communicating trade-offs and supporting strategic decisions. • Collaborate with Engineering and AI teams to integrate models, embeddings, and external components, establishing strong, reliable partnerships. • Identify opportunities for standardization — documentation, templates, automations, and workflows — bringing systemic vision and problem-solving capability in complex scenarios.

🎯 Requirements

• Proven experience as an SRE in high-scale environments, with strong analytical ability and mature decision-making. • Proficiency with Kubernetes, observability (Prometheus, OpenTelemetry, Grafana), infrastructure as code (Terraform), and SRE practices (SLO/SLI, incident response, advanced troubleshooting). • Experience with MLOps, inference pipelines, or platforms running AI models in production. • Experience with AWS (EKS, IAM, messaging, monitoring), distributed architecture, security, and multi-tenancy. • Clear and collaborative communication skills, ability to navigate ambiguity, and a partnership mindset across multiple teams. • Ability to prioritize, manage risk, and deliver consistently in complex environments.

🏖️ Benefits

•