GCP GenAI Engineer

Key Responsibilities:

• Design and develop Generative AI/LLM-based applications on GCP.
• Work with Vertex AI, Gemini models, Model Garden, Vertex AI Studio, and related GCP AI services.
• Develop RAG (Retrieval-Augmented Generation) solutions using enterprise data.
• Build and optimize prompt engineering, embeddings, vector search, and LLM workflows.
• Integrate LLMs with APIs, enterprise applications, databases, and data platforms.
• Develop AI solutions using Python and frameworks such as LangChain/LangGraph.
• Work with Vertex AI Vector Search or other vector databases.
• Implement model evaluation, monitoring, security, governance, and responsible AI practices.
• Deploy scalable AI applications using Cloud Run, GKE, Cloud Functions, or similar GCP services.
• Work with BigQuery, Cloud Storage, Pub/Sub, Dataflow and other GCP data services.
• Implement CI/CD and MLOps practices for GenAI applications.
• Collaborate with data scientists, ML engineers, software developers, and business teams.
• Troubleshoot performance, latency, scalability, and cost issues in GenAI workloads.

Mandatory Skills:

• Strong hands-on experience with GCP.
• Experience with Vertex AI and Gemini/LLM models.
• Strong Python programming skills.
• Hands-on experience in Generative AI, LLMs, RAG, Prompt Engineering.
• Experience with embeddings and vector databases/vector search.
• Experience with LangChain/LangGraph or similar GenAI frameworks.
• Good understanding of REST APIs, microservices, and cloud architecture.
• Experience with Docker and Kubernetes/GKE.
• Knowledge of BigQuery and Cloud Storage.
• Understanding of MLOps, CI/CD, model deployment and monitoring.

Good to Have:

• Experience with Gemini APIs and Vertex AI Agent Builder/Agent Development Kit.
• Knowledge of Terraform/IaC.
• Experience with AI agents and multi-agent architectures.
• Knowledge of Responsible AI, model safety, and AI governance.
• GCP certification such as Professional Machine Learning Engineer or Professional Cloud Architect.