Job Summary: We are seeking an LLMOps Engineer to support and evolve our AI technological foundation, ensuring high availability, security, and cost efficiency for AI Gateway and Agent Orchestration platforms. Key Highlights: 1. Support the maintenance and evolution of AI Gateway and Orchestration platforms. 2. Ensure high availability, security, and cost efficiency for AI. 3. Build tools that multiply developer productivity. **What We’re Looking For?** ***LLMOps Engineer / AI Platform Engineer*** We are looking for an LLMOps Engineer to support the maintenance and evolution of our AI technological foundation. Your mission will be to ensure that our AI Gateway and Agent Orchestration platforms operate with high availability, security, and cost efficiency. You will serve as the “right-hand” of infrastructure for development teams, providing the necessary tools, access, and monitoring so they can build solutions atop our platforms. You must possess at least a basic understanding of how an Agent works (concepts learned and low-code or code-based agent creation), but your daily focus will be on the “plumbing” that enables all of this to function at scale. **Key Responsibilities:** * AI Gateway Management: Manage and evolve the proxy layer that centralizes calls to models (Azure OpenAI, AWS Bedrock, GCP Vertex AI), configuring rate limiting, failover (model fallback), caching, and load balancing. * RAG Infrastructure: Provision, optimize, and monitor managed Knowledge Base and Vector services (e.g., AWS OpenSearch, Azure AI Search, AWS Knowledge Bases, Google Vertex AI Vector Search). * Multi-Cloud Operations: Serve as the technical expert on GenAI services across major cloud providers (AWS, Azure, GCP), managing quotas, permissions (IAM), and private security configurations (VPCs, Private Links) for model access. * LLM Observability: Implement tracing and monitoring tools (e.g., LangSmith, LangFuse, Arize, Datadog AI, Grafana) to track latency, token usage, costs, and errors in real time. * AI Automation and CI/CD: Create automated pipelines that not only test code but also run prompt evaluations (Evals) and model regression tests before production deployment. * AI FinOps: Closely monitor inference costs, set budget alerts, and propose optimizations. **Requirements:** * AI Engineering Fundamentals: Solid understanding of how LLMs, embeddings, agents, and RAG work, enabling effective collaboration with developers. * Cloud Provider (GenAI) Proficiency: Hands-on experience configuring services such as Amazon Bedrock, Azure OpenAI Service, or Google Vertex AI. * Programming Languages: Proficiency in Python (for automation scripts, AI SDKs, and pipelines) and TypeScript (commonly used in edge gateways and proxies). * Infrastructure as Code (IaC): Experience with Terraform to provision AI resources reproducibly. * Containerization and Orchestration: Strong expertise in Docker and Kubernetes (EKS/AKS/GKE) to sustain the Agent platform. * APIs and Gateways: Deep understanding of REST, gRPC, and API Gateway operation (Kong, APIGee, or AI-specific solutions such as Portkey/Helicone). **Preferred Qualifications:** * Cloud Certifications (Highly Desired): * AWS Certified AI Practitioner. * Microsoft Certified: Azure AI Engineer Associate. * Google Cloud Professional Machine Learning Engineer. * Experience implementing Local LLMs (vLLM, Ollama) on on-premises infrastructure (GPUs) to reduce costs. * Knowledge of AI security (OWASP Top 10 for LLM, sensitive data/PII masking at the gateway). **Behavioral Profile:** * Platform Mindset: Enjoys building tools that multiply other developers’ productivity. * Operational Resilience: Will not rest until understanding why a request failed or why latency increased. * Cloud-Agnostic Curiosity: Interested in understanding nuances and differences among AWS, Azure, and Google services to recommend the best tool for the job. **Desired Academic Background:** * Bachelor’s degree in Computer Science, Software Engineering, Network Engineering, or a related technical field. * Master’s degree or specialized courses in Machine Learning/AI, MLOps, or Cloud Computing are considered advantageous. **Location of the Position:** **Why Build Your Career at Meta?** We offer autonomy, clear goals, and a dynamic, challenging environment where professionals have opportunities to interact with diverse technologies, participate in all types of projects, bring new ideas, and work from anywhere in Brazil—and why not, the world? Additionally, we are one of the best companies to work for in Brazil according to Great Place to Work and among the top 10 fastest-growing companies in the country for three consecutive years, per the Informática Hoje Annual Report. **What Are Our Values?** * We are people serving people. * We think and act like owners. * We have a drive for performance. * We grow and learn together. * We pursue excellence and simplicity. * Innovation and creativity are in our DNA. All individuals are welcome regardless of their condition, disability, ethnicity, religious belief, sexual orientation, appearance, age, or similar attributes. We want you to grow with us in an inclusive, opportunity-rich environment. If this resonates with you, then #JoinMeta!