About this role
Architect large language models (LLM) that process and generate natural language and design neural network parameters trained on large text corpora. Hands-on engineering role to design, build, integrate, test and operationalize enterprise-grade LLM, GenAI and agent components on GCP, including RAG pipelines, retrieval, safety controls and production deployment.
Skills for this role
Large Language Models (LLMs)Google Cloud Platform (GCP)Google Cloud Data ServicesVertex AIGemini Enterprise Agent PlatformGemini modelsModel GardenAgent BuilderAgent EngineVertex AI SearchBigQueryAlloyDBCloud SQLCloud RunGKEPub/SubCloud FunctionsIAMCloud LoggingCloud MonitoringRAGFunction callingTool callingAgent orchestrationPrompt engineeringEmbeddingsVector databasesEvaluation metricsPythonAPIs''Distributed systems''CI/CD''Automated testing''Observability''Secure