Retrieval-Augmented Generation (RAG)
Built RAG pipelines augmenting LLMs with real-time retrieved context from vector stores and knowledge bases. Implemented semantic search layers, chunking strategies, and embedding models for domain-specific AI systems at 1C Platform and Neural Mindmap.
I built RAG pipelines at 1C Platform and Neural Mindmap that augmented LLMs with real-time retrieved context from vector stores and knowledge bases. The RAG system retrieved relevant documents based on semantic similarity, then passed them as context to the LLM, producing answers grounded in the company's own data.
Chunking strategy was the most impactful design decision. I experimented with fixed-size chunks, sentence-based chunks, and semantic chunks, finding that semantic chunks (grouping related sentences) produced the best retrieval quality. The chunking strategy improved answer accuracy from 76% to 89%.
Embedding model selection mattered as much as chunking. I benchmarked multiple embedding models on domain-specific queries, finding that domain-adapted embeddings outperformed general-purpose ones by 12% on retrieval accuracy. The investment in benchmarking paid off in every downstream metric.
At 1C Platform and Neural Mindmap, the RAG pipelines I built augmented LLMs with real-time retrieved context from vector stores and knowledge bases, producing answers grounded in the company's own data rather than the model's training corpus. The semantic chunking strategy, grouping related sentences, improved answer accuracy from 76% to 89% compared to fixed-size chunks.
The embedding model benchmarking I conducted at Neural Mindmap compared multiple models on domain-specific queries, finding that domain-adapted embeddings outperformed general-purpose ones by 12% on retrieval accuracy. The investment in benchmarking paid off in every downstream metric, as better retrieval produced better answers, which produced better user trust and adoption.
Related Skills
Explore the Full Portfolio
This is the complete portfolio of Sufi Khan Sulaiman, a technology leader specialising in B2B commerce and digital automation. Start from the Home page for the overview, then move through two decades of career experience across FLIR Systems, Lorex Technology, and 1c Platform, and the full catalogue of project case studies spanning headless commerce migrations, AI recommendation engines, and multi-channel fulfilment systems.
The skills and certifications page maps the technical and leadership capabilities behind the work, while the articles and the knowledge base break down the thinking into actionable frameworks. For hands-on learning, the tutorials and applications sections cover practical builds from front-end fundamentals to full-stack web apps.
For consulting engagement, the expertise page outlines service offerings, the ecommerce hub covers platform architecture and automation strategy, and the ecommerce guide (PDF) is a downloadable 55-page field manual. When you are ready to talk, the contact page is the direct line.