Intent resolution, hybrid retrieval, and response assembly for a domain-specific AI assistant.
Open for work
Ziad El Fatih
Applied AI & Data Engineer
Building intelligent systems through retrieval, orchestration, and durable data pipelines.
systems / data / retrieval / intelligence
About
I work across applied AI, search, retrieval, and data infrastructure. Most of the systems here live where product behavior depends on architecture holding up under real complexity.
Index
Current focus
- AI systems and orchestration
- Search and retrieval architecture
- Data platforms for AI products
Systems
Systems and architectures.
A small set of systems that show how I think about architecture, tradeoffs, and real-world constraints.
Extraction, enrichment, embedding, and indexing pipeline for retrieval-ready document systems.
A unified retrieval interface for chat, search, and filtered discovery across the product surface.
Writing
Notes on systems, search, and AI infrastructure.
Writing here is mostly a way to think clearly in public.
2025
Hybrid search becomes a systems design problem once score normalization, query routing, and operational tuning enter the picture.
2025
Most RAG stacks move too quickly from prompt to retrieval. A resolver layer improves precision by decomposing intent, extracting entities, and converting ambiguous language into structured search actions.
2024
When the downstream consumer is a retrieval system or model instead of an analyst, pipeline design tolerances shrink. Chunking, metadata quality, schema stability, and data contracts become product-level concerns.
Experience
Background in data engineering and applied AI.
Brief notes on where I have built and what I have been responsible for.
2025 - 2026
Senior Data Engineer / AI Engineer
Plastik AI
Architected a hybrid retrieval system combining vector embeddings, structured search, and LLM orchestration enabling AI-driven materials discovery across 20M+ engineering material records.
2022 - 2024
Senior Data Engineer
DeepSearch Labs
Built a multimodal intelligence and semantic search platform. Led design and implementation of data infrastructure, including ETL pipelines, data models, and search indexing for large-scale multimodal datasets.
2019 - 2022
Data Engineer / Consultant
Go & Dev Consulting
Designed ETL pipelines, data models, and analytics infrastructure across client environments with different levels of technical maturity.