Engenheiro de Dados e Plataforma de Agentes Sênior (GCP)
Core
Design and build scalable data infrastructure and AI-powered solutions within the Google Cloud Platform ecosystem, preparing high-quality data for production-grade AI applications and intelligent agents.
Role type
Senior Data Engineer & Agent Platform Engineer
Builds
Scalable data pipelines, Data Lake/Lakehouse architectures, RAG solutions, LLMOps pipelines, and agent-based systems
Domain
Healthcare technology, Google Cloud Platform (GCP), AI Infrastructure
Deliverable
production ML models
Required skills
Python, SQL, Google Cloud Platform (BigQuery, Dataflow, Dataproc, Pub/Sub, Cloud Storage), Data orchestration (Cloud Composer/Airflow), Terraform, CI/CD, Distributed architectures, Data governance, LGPD compliance
Preferred skills
Vertex AI services (RAG Engine, Search, Agent Engine), MCP servers, Vector databases, Healthcare data standards (HL7, FHIR), Data Mesh, FinOps
Technologies
BigQuery, Dataflow, Dataproc, Pub/Sub, Cloud Storage, Cloud Composer, Airflow, Terraform, Cloud Build, GitHub Actions, Vertex AI, Model Armor, OpenTelemetry, Cloud Logging, Cloud Monitoring, Cloud Trace
Responsibilities
Design and maintain batch and streaming data ingestion pipelines; Build scalable Data Lake and Lakehouse architectures; Define and maintain data contracts and quality monitoring; Prepare and optimize datasets for AI applications (RAG, embeddings); Ensure compliance with LGPD for sensitive healthcare data; Design secure cross-project data access architectures; Enable internal systems as tools for AI agents via MCP servers; Develop and maintain MLOps and LLMOps pipelines; Provision and manage infrastructure as code; Implement FinOps practices; Establish end-to-end observability; Contribute to resilience and disaster recovery strategies; Collaborate with data scientists, AI teams, and stakeholders.
Seniority
Senior, hands-on IC
