cat intro.txt
AI Systems Engineer
Makeen Majlis
I build production AI systems for search, document intelligence, retrieval, automation, and knowledge-intensive software.
I turn large, complex datasets and document collections into reliable products using semantic search, hybrid retrieval, RAG, multilingual processing, and scalable backend infrastructure.
inspect services/
Systems built around difficult knowledge problems.
Engagements are scoped around a concrete workflow, corpus, or product—not a generic AI feature list.
Private, source-grounded assistants and research tools built around your documents, data, and workflows.
02Search and retrieval infrastructureSemantic, full-text, and hybrid search systems for large or multilingual collections.
03Document intelligenceIngestion systems that turn PDFs, scans, audio, and inconsistent source files into structured, searchable data.
04Custom AI softwarePurpose-built SaaS products, internal tools, and workflow automation around a specific operational problem.
Featured system · live
Istidlal
A production research system that combines multilingual retrieval, source verification, and structured AI answers.
Istidlal ingests, structures, indexes, and retrieves a large multilingual corpus. It combines semantic and full-text retrieval, reranking, citation assembly, and answer generation inside a production application with identity, subscriptions, and source-reading workflows.
- 01
- Hundreds of classical books
- 02
- Hundreds of thousands of indexed passages
- 03
- Multilingual source retrieval
- 04
- Live production system
ls projects/
Selected products and infrastructure.
Live systems and active builds across research, document search, collaboration, and domain-specific software.
./start_project.sh
Have a difficult search, document, or AI workflow?
Send the problem, the data involved, and what a useful outcome would look like. I'll tell you whether I can help.