About The Role
The Full Stack AI Engineer leads the design and delivery of production-grade AI and agentic solutions built on Google Cloud Platform (GCP). Operating as a hands-on technical leader and Forward Deployed Engineer, you will work directly with stakeholders to translate business challenges into scalable AI applications using Google Cloud’s AI, data, application, and infrastructure capabilities.
You will combine deep GCP engineering expertise with client leadership, remaining actively involved in architecture, development, code reviews, and production delivery.
Key Responsibilities
Architect and deliver end-to-end GenAI and agentic AI solutions using Vertex AI, Gemini models, Vertex AI Agent Engine, Agent Development Kit (ADK), Model Garden, and Google Cloud APIs.
Design agent architectures including multi-agent, supervisor/worker, event-driven and parallel orchestration patterns, tool calling, MCP integration, agent-to-agent coordination, and reusable agent skills.
Build enterprise knowledge and retrieval solutions using Vertex AI, BigQuery, AlloyDB, Cloud SQL, Vector Search, enterprise search, RAG, Text-to-SQL, and knowledge graph patterns.
Develop full-stack AI applications using Python, modern frontend technologies, APIs and microservices deployed through Cloud Run, Google Kubernetes Engine (GKE), API Gateway, and containerized environments.
Establish production MLOps, LLMOps and AgentOps practices, including automated evaluation, CI/CD, model and prompt lifecycle management, observability, tracing, drift monitoring, latency optimisation, and cost controls.
Implement enterprise AI security and governance using appropriate Google Cloud capabilities, including IAM, Secret Manager, Cloud Logging, Cloud Monitoring, VPC Service Controls, encryption and data protection controls.
Lead technical workshops, translate business requirements into GCP solution architectures, develop value hypotheses, and communicate architectural decisions to technical and non-technical stakeholders.
Lead and develop engineering teams through architecture reviews, code reviews, technical coaching, and hands-on problem solving while contributing reusable GCP AI accelerators and reference architectures.
Required Qualifications
Proven hands-on experience designing and deploying AI/ML, Generative AI or agentic applications on Google Cloud Platform in production.
Strong experience with Vertex AI and Gemini, including the development of LLM-powered applications, agents, tools, and enterprise AI workflows.
Hands-on experience with Google Cloud data technologies such as BigQuery, Cloud Storage, AlloyDB, Cloud SQL, Pub/Sub, or Dataflow.
Strong full-stack engineering skills, including Python, APIs/microservices, and a modern frontend or application framework.
Experience with cloud-native application engineering using Cloud Run and/or GKE, containers, CI/CD, infrastructure as code, and production operations.
Experience designing enterprise RAG, semantic search, Text-to-SQL, vector retrieval, or knowledge-layer architectures.
Proven experience engaging stakeholders and translating complex business requirements into scalable technical solutions.
Preferred Qualifications
Experience with Google Cloud Agent Development Kit (ADK), Vertex AI Agent Engine, MCP, multi-agent architectures, and agent evaluation.
Experience implementing cloud security and responsible AI controls in enterprise environments.
Experience with Terraform, Cloud Build, Artifact Registry, Cloud Logging and Cloud Monitoring.
Relevant Google Cloud certifications, particularly Professional Cloud Architect, Professional Machine Learning Engineer, or Professional Data Engineer.