مهندس أول ذكاء اصطناعي وبيانات (منصة Google Cloud)

ZTechnium is looking for an experienced, hands-on Sr. AI & Data Engineer to design, develop, and own the end-to-end Data and AI pipeline for an enterprise AI Insights platform built on Google Cloud Platform (GCP).

The solution integrates structured enterprise data, operational systems, and document repositories to provide AI-powered analytics, natural-language querying, intelligent reporting, and knowledge retrieval.

The ideal candidate combines strong Python and data engineering experience with practical expertise in Vertex AI, Gemini, BigQuery, RAG, and production-grade AI orchestration.

This is a hands-on engineering role requiring architectural ownership and active implementation, not just technical supervision.

Key Responsibilities

1. Data Engineering & Integration

• Design and implement end-to-end data ingestion, transformation, and processing pipelines.
• Integrate enterprise applications through REST APIs and approved enterprise integration gateways.
• Build structured data pipelines for analytical queries, KPIs, aggregations, and reporting.
• Develop and optimize data models and analytical queries using BigQuery, PostgreSQL, and SQL.
• Implement data validation, reconciliation, quality checks, and efficient data refresh mechanisms.

2. Generative AI & AI Orchestration

• Design and implement AI services using Google Vertex AI and Gemini models.
• Build AI orchestration pipelines supporting intent classification, tool calling, structured data queries, and conversational interactions.
• Develop Retrieval-Augmented Generation (RAG) solutions for enterprise document knowledge bases.
• Implement document ingestion, parsing, chunking, embeddings, vector indexing, and semantic retrieval.
• Build hybrid AI workflows combining structured operational data with unstructured enterprise documents.
• Ensure AI-generated answers are grounded in verified enterprise data, with accurate citations and traceability.

3. Google Cloud Engineering

• Design and deploy AI and data workloads using GCP services such as:
• Vertex AI / Gemini
• BigQuery
• Cloud Run and Cloud Run Jobs
• Cloud SQL / PostgreSQL
• Pub/Sub and Cloud Tasks
• Cloud Storage
• Vertex AI Vector Search or pgvector
• Cloud Logging and Monitoring
• Optimize cloud infrastructure usage, AI model consumption, latency, scalability, and operating costs.
• Collaborate with DevOps engineers on secure deployment, monitoring, and CI/CD processes.

4. AI Quality, Performance & Governance

• Implement AI evaluation frameworks to measure answer accuracy, retrieval relevance, and grounding quality.
• Ensure numerical accuracy through deterministic business logic and validated analytical results.
• Implement data-access controls, sensitive-data protection, auditability, and secure AI service integration.
• Develop monitoring and troubleshooting mechanisms for AI pipelines and data-processing jobs.
• Optimize performance using caching, efficient retrieval, asynchronous processing, and model-routing strategies.

5. Technical Ownership & Collaboration

• Own the architecture, implementation, and technical delivery of the Data and AI components.
• Collaborate with backend, frontend, cloud, and QA engineers.
• Produce architecture diagrams, technical documentation, and integration specifications.
• Participate in technical discussions, solution design workshops, and production troubleshooting.
• Support testing, deployment, knowledge transfer, and operational handover.

Required Qualifications

• 5+ years of professional software engineering or data engineering experience.
• Strong hands-on experience with Python and SQL.
• Proven experience building production data-processing pipelines.
• Practical experience with Google Cloud Platform, particularly Vertex AI, BigQuery, and Cloud Run.
• Experience building production Generative AI applications using LLM APIs.
• Strong understanding of RAG, embeddings, vector databases, semantic search, and AI orchestration.
• Experience integrating external enterprise systems and APIs.
• Knowledge of PostgreSQL, data modelling, query optimization, and data validation.
• Experience developing backend services using FastAPI or similar Python frameworks.
• Strong debugging, system design, and performance optimization skills.
• Ability to independently own and deliver complex technical components from architecture through production.

Nice to Have

• Google Cloud Professional Data Engineer or Professional Machine Learning Engineer certification.
• Experience with Google Agent Development Kit (ADK), LangGraph, or similar orchestration frameworks.
• Experience with IBM API Gateway / ESB integrations.
• Experience integrating Azure Blob Storage or SharePoint document repositories.
• Experience with Document AI, OCR, and enterprise document processing.
• Knowledge of Terraform, CI/CD, IAM, and cloud security best practices.
• Previous experience delivering enterprise AI analytics, compliance, or reporting platforms.

What Success Looks Like

The successful candidate will deliver:

• Reliable, validated pipelines integrating approved enterprise data sources.
• Governed analytical data services supporting accurate KPIs, comparisons, and reports.
• A production-ready RAG pipeline for approved enterprise documents.
• A secure AI orchestration layer that combines structured and unstructured information.
• Accurate, traceable AI responses with appropriate performance, monitoring, and access controls.
• Documented, tested, maintainable AI and data components ready for production deployment.

How to apply

Please share your CV along with a brief description of a production AI or data engineering solution you have personally designed and implemented.

We are particularly interested in candidates who have worked on end-to-end Generative AI solutions using Google Cloud Platform, rather than standalone chatbot prototypes.