Senior AI Context Engineer

Responsibilities

• Design and implement enterprise semantic models and certified KPI layers to ensure trusted, reusable business metrics.
• Build AI-safe data abstraction layers that prevent metric recomputation and ensure consistency across analytics and AI use cases.
• Develop and enforce data contracts, metadata standards, and semantic governance frameworks across domains.
• Engineer scalable batch and real-time streaming data pipelines in a modern cloud environment (GCP preferred).
• Collaborate with AI/ML teams to design reliable grounding strategies for AI applications and agents.
• Implement metadata management capabilities including cataloging, lineage, observability, and automated data quality checks.
• Apply Data Ops principles including CI/CD, automated testing, and deployment automation for data products.
• Support domain-oriented and microservices-based data architecture patterns.
• Mentor engineers and promote best practices in semantic modeling, governance, and AI‑ready platform design.

• 10–15+ years of experience in enterprise‑scale cloud data engineering and distributed systems.
• Strong hands‑on experience building modern data platforms in GCP (Big Query, Dataform, Pub/Sub, Composer/Airflow, Cloud Run).
• Deep expertise in SQL, Python, and data modeling (dimensional modeling, lakehouse architectures).
• Experience with open‑source tech stack such as Iceberg, Trino, Kubernetes, Docker etc.
• Hands‑on experience with metadata management, lineage tracking, observability, and data quality frameworks.
• Experience building both batch and real‑time streaming data systems.
• Strong understanding of semantic modeling, business metric governance, and AI consumption patterns.

• Data Modeling
• Dimensional Modeling
• Lakehouse Architectures
• Batch Data Systems
• Real‑Time Streaming Data Systems
• Data Quality Frameworks
• Lineage Tracking
• Observability
• Data Ops Principles
• Automated Testing

• Mentoring
• Collaboration