shehabibrahim

Lead developer of a centralized LLM Gateway (LiteLLM) unifying AI access for multiple enterprise products. Designed a modular RAG framework supporting configurable embeddings, indexing, and retrieval with PGVector and LangChain. Built a scalable document-processing pipeline (text extraction, summarization, translation, embeddings) using AWS SQS/SNS. Optimized system throughput by decoupling real-time and background APIs for reliability. Collaborate across distributed AI, product, and infrastructure teams to ensure scalability and security in multi-tenant environments.

Worked closely with AI and product teams to enhance enterprise search and recommendation systems. Improved median search response times by 31% through adaptive Solr replica selection and optimized caching strategies. Designed microservices and ETL pipelines supporting document recommendation for 200K+ enterprise users. Led backend integrations and contributed to architectural decisions for large-scale distributed systems.

Developed robust backend systems for KYC/KYB verification ensuring scalability and performance. Conducted unit testing, implemented CI/CD pipelines, and mentored new developers.

Fixed core engine bugs and updated documentation for Sencha UI projects improving system stability.