AI Engineer – GenAI G Cloud Solutions (GCP)

Job Requirements

Design, develop, and deploy AI/ML and GenAI solutions using GCP-managed
services.
Lead the implementation of advanced RAG pipelines leveraging knowledge graphs,
agent-based retrieval strategies, and structured data extraction (Text2SǪL).
Collaborate with cross-functional teams to integrate AI solutions into cloud-native
architectures and customer-facing applications.
Optimize model performance, latency, and scalability for production-grade
deployments.
Build and manage pipelines for document ingestion, vector indexing, and contextual
retrieval using modern RAG frameworks.
Utilize and integrate GCP tools such as Vertex AI, Cloud Functions, BigǪuery, and
Gemini APIs.
Contribute to the adoption and implementation of MCP and Google A2A to enable
complex multi-agent interactions and workflows.
Write clean, scalable, and efficient code in Python to support AI workflows, APIs, and
automation pipelines.

Minimum 3+ years of professional work experience in AI/ML engineering, or related
roles.
Excellent problem-solving skills and the ability to architect scalable and modular AI
solutions.
Minimum 3+ years of hands-on Python programming experience, with strong
proficiency in building AI pipelines, automation, or backend systems.
Proven experience with Google Cloud Platform (GCP) for AI/ML development and
deployment.
Hands-on production implementation of Generative AI systems (chatbots, RAG
solutions, etc.) on cloud infrastructure.
Expertise in Advanced RAG techniques: Knowledge Graph RAG, Agentic RAG, and
Text2SǪL RAG.
Solid understanding of MCP (Model Context Protocol) and Google Agent to Agent
(A2A) frameworks.

GCP Professional Certification – Cloud Architect or Machine Learning Engineer.
Experience with vector and graph databases.
Familiarity with LLM fine-tuning, prompt engineering, and multi-agent orchestration.
Experience with CI/CD and containerization (Docker, Kubernetes).

"*" indicates required fields