As a GCP Engineer specializing in Agentic AI, you will be at the forefront of developing and managing cutting-edge AI infrastructure. You will leverage your expertise in Google Cloud Platform to create robust, scalable, and secure environments for our AI applications. Your work will span the entire AI lifecycle, from pipeline orchestration and data engineering to advanced deployment strategies and comprehensive infrastructure management. We are looking for a proactive individual who can champion best practices in data and AI governance, ensuring our systems are not only performant but also reliable and compliant. This role requires hands-on experience with Agentic AI concepts, strong Python programming skills, and a deep understanding of GCP services.

• AI Pipeline & Orchestration:
• Design and manage end-to-end AI agent build pipelines using Vertex AI Pipelines.
• Automate data ingestion, feature engineering, training, evaluation, and deployment workflows.
• Implement reproducible experiments and pipeline versioning.
• Data Engineering & Storage:
• Work with BigQuery for large-scale analytics and training datasets.
• Manage datasets and artifacts in Google Cloud Storage.
• Implement data lineage tracking for traceability and governance.
• Infrastructure & CI/CD:
• Implement Infrastructure as Code (IaC) using Cloud Build, Terraform, or similar tools for provisioning and managing GCP resources.
• Build CI/CD pipelines for AI agent training and deployment.
• Manage source control and collaboration using Git.
• Containerization & Deployment:
• Containerize AI workloads using Docker.
• Deploy batch and real-time Agent builds using Cloud Run Services, Cloud Run Jobs, or Openshift cluster/GKE (Google Kubernetes Engine) for more complex, scalable microservices architectures (if applicable).
• Implement deployment strategies such as blue-green, canary, and rollback.
• LLM, RAG & Vector Databases:
• Build and deploy LLM-powered applications.
• Implement Retrieval-Augmented Generation (RAG) pipelines.
• Integrate and manage Vector Databases for embeddings and semantic search.
• AI Agent/Model Lifecycle Management:
• Implement AI agent/model lineage tracking and versioning.
• Monitor AI agent/model performance, drift, and data quality in production.
• Set up alerting and dashboards for AI agent/model health.
• Cloud Infrastructure Management & Optimization:
• Design and manage secure, scalable, and cost-effective GCP infrastructure components, including networking (VPCs, firewalls, load balancers), compute (GCE, Openshift, GKE), and storage.
• Implement and enforce security best practices and IAM policies across the GCP environment.
• Proactively monitor and optimize GCP resource utilization and costs.
• Troubleshoot and resolve infrastructure-related issues impacting AI workloads.
• Packaging & Development:
• Develop production-grade AI agent services using Python or other relevant languages.
• Package reusable AI components and libraries using PyPI or other appropriate methods.
• Follow best practices for code quality, testing, and documentation.

Required Skills & Experience:

• Technical Skills:
• Strong experience with GCP services (Vertex AI, BigQuery, GCS, Cloud Run, GKE, Compute Engine, Cloud Networking).
• Solid understanding of AI algorithms and training workflows.
• Hands-on experience with LLMs, RAG, and vector search systems.
• Proficiency in Docker, Git, and CI/CD pipelines.
• Strong Python programming skills.
• Experience with infrastructure as code tools like Terraform or Cloud Deployment Manager.
• Data and AI Governance:
• Experience with data and AI agent/model lineage.
• Knowledge of AI agent/model monitoring, drift detection, and observability.
• Understanding of scalable AI agent deployment patterns.
• Strong understanding of GCP security principles, IAM, and network security.

Good to Have:

• Experience with feature stores.
• Familiarity with MLflow or similar experiment tracking tools.
• Experience with cost optimization on cloud platforms.