About the role

What you’ll do

• Design, develop, and deploy enterprise-grade AI agents and Generative AI solutions on Google Cloud Platform
• Implement Retrieval-Augmented Generation architectures for document ingestion, retrieval, and response generation
• Build agentic and multi-agent systems using LangChain and orchestration frameworks
• Deploy cloud-native and containerized applications with Docker, Kubernetes, microservices, and serverless architectures
• Apply automation testing to ensure reliable AI deployments
• Provide technical leadership and deliver AI transformation initiatives

What you’ll need

• Strong hands-on experience with Google Cloud Platform and Vertex AI for enterprise-scale Generative AI
• Proven expertise in RAG, embeddings, vector databases, semantic search, and grounding techniques
• Extensive experience with Agentic AI and multi-agent systems using LangChain
• Advanced programming skills in Python plus enterprise application development in Java, C#, or Node.js
• Strong knowledge of SQL and NoSQL databases, data modeling, and integration
• Solid background in DevOps, CI/CD, MLOps, and AI model lifecycle management

Original job description