Job Summary

Job Title: AI Engineer, Google Cloud Specialist

Experience Level: Mid-Level (3-4 Years)

Role Overview

We are seeking a results-driven and technically sharp AI Engineer to be the core builder of our AI-powered products on Google Cloud. You will be responsible for translating architectural designs into robust, scalable, and production-ready code. This is a hands-on-keyboard role where you will own critical components of our AI services, from data ingestion pipelines to model deployment and API development. You are expected to be a strong Python developer and a proficient practitioner across the Google Cloud and Vertex AI ecosystems, capable of turning complex requirements into effective, maintainable software.

Key Responsibilities

- Own and Ship Production AI Services: Take full ownership of developing, testing, deploying, and monitoring AI-powered microservices. You will be responsible for the end-to-end lifecycle of the components you build, ensuring they meet strict performance and reliability SLAs.
- Develop and Optimize Data Pipelines: Engineer and maintain scalable data pipelines using Dataflow and BigQuery for training data preparation, feature engineering, and inference logging. You will be expected to write and optimize complex SQL and Apache Beam code.
- Productionize ML Models: Implement robust MLOps workflows using Vertex AI Pipelines and Cloud Build. This includes creating custom pipeline components for data validation, model testing, and secure deployment to Vertex AI Endpoints. You will be responsible for the automation that enables rapid and safe iteration.
- Build Production-Grade RAG Systems: Develop and productionize key components of Retrieval-Augmented Generation (RAG) applications. This involves implementing the retrieval logic using Vertex AI Search, processing and embedding documents for vector search, and integrating context-aware results into prompts for the Gemini API.
- Performance Tuning and Cost Management: Proactively identify and resolve performance bottlenecks in your code and infrastructure.



You will be responsible for writing efficient code and configuring GCP services (e.g., BigQuery clustering, Cloud Run concurrency) for optimal cost and performance.

Core Technical Stack
- Compute: GKE, Cloud Run, Cloud Functions Deploy, manage, and troubleshoot containerized applications. Write Kubernetes manifests (Deployment, Service). Configure autoscaling and IAM roles for services.
- Databases/Storage: BigQuery, Cloud SQL (Postgres), Cloud Storage, Memorystore (Redis). Write complex, cost-optimized SQL (window functions, CTEs). Design table schemas with partitioning/clustering. Use Cloud SQL as a backend for applications.
- Data Processing: Dataflow (Apache Beam), Pub/Sub, Dataproc (basic). Author and debug batch and streaming Dataflow jobs using Python SDK. Design resilient data ingestion flows with Pub/Sub. Run occasional Spark jobs for data exploration.
- MLOps Automation: Vertex AI Pipelines, Cloud Build, Artifact Registry, Terraform. Author and debug ML pipelines from scratch. Create custom Python components for pipelines. Write CI/CD configurations in cloudbuild.yaml. Manage Docker images. Write and apply basic Terraform modules.
- Vertex AI Platform: Endpoints, Model Monitoring, Workbench/Colab Enterprise, GenAI Studio. Deploy models to endpoints with appropriate machine types. Configure monitoring for prediction drift and skew. Use notebooks for exploration and prototyping. Test prompts in the Studio.
- Generative AI: Gemini API, Vertex AI Search, LangChain. Make direct API calls to Gemini for multimodal and text tasks. Implement RAG logic by querying Vertex AI Search and constructing context-aware prompts. Use LangChain for rapid prototyping.
- Classic ML: TensorFlow/PyTorch, Scikit-learn, Pandas, NumPy. Implement, train, and evaluate standard models for classification, regression, and clustering. Perform feature engineering and data preprocessing. Understand model trade-offs.
- Programming: Python, SQL, Docker, Git. Write clean, testable, and efficient Python code (expert). Write complex SQL queries (expert). Build and debug Docker containers. Use Git for version control following team practices (e.g., branching, PRs).

📌 Senior Analyst - Gen AI (Chennai)
🏢 enGen Global
📍 Chennai