Content revision 4e771eaf0390cc87b6c7c6fd8469f3508f6ceeec7119472e6c1ccf17e2e1e5d2

## Cloud, Data & AI Consulting Intern

Experience
Source ID experience:pwc
Original https://www.henryw.me/#/experience#work-pwc

At PwC, I work on AI and data systems for financial-services and public-sector clients, combining solution architecture with hands-on development. I translate business needs into technical requirements and evaluate how existing tools can work together within the client’s constraints. Through rapid prototyping, I build and run end-to-end proofs of concept to test the proposed solution against real workflows and refine the design.

I designed a system that uses AI to identify gaps in an IT assistant’s knowledge, research the missing information and keep its knowledge base up to date. I also built a browser agent that interprets service tickets and carries out tasks in the applications the team already uses.

For an AI assistant answering public enquiries using client documents, I evaluated and integrated tools into a RAG ingestion pipeline that prepares those documents for retrieval. It preserves page-spanning content, complex tables, references and flowcharts through chunking, which divides documents into searchable passages. I also developed a DeepEval framework to evaluate classification, retrieval and response quality.

To support a data migration, I built an LLM-assisted pipeline that reverse-engineers legacy ETL code, the logic that extracts, transforms and loads data. It recovers data lineage showing where data comes from and how it changes, together with the business rules and test scenarios needed for the migration.

I evaluated enterprise document-processing systems and built workflows to recover information lost during preprocessing and support rule-based document review.

I reviewed Ethereum and stablecoin infrastructure risks for a banking engagement.

## A Structure-Preserving RAG Ingestion Pipeline

Builds
Source ID projects:pwcRag
Original https://www.henryw.me/#/projects?to=pwcRag

The architectural risk appeared before retrieval began. If ingestion separated a passage from the note it refers to or reduced a flowchart to disconnected text, no later ranking or generation step could reliably restore the missing relationship.

MinerU rejoined paragraphs and tables across page breaks. Its OCR-based path recovered merged cells but missed nested tables in the tests. The built-in visual-language model recovered both as HTML. I then found that subsequent processing in the tested RAGFlow path discarded those tags, while LlamaIndex preserved the structure through indexing, retrieval and answer generation.

Cross-page footnotes and remarks needed explicit linking. I wrote a Python linker that used reference labels and document context to attach each note to its citing text before chunking. For flowchart images, I chose Mermaid to represent nodes and branches as searchable text that could be rendered back for inspection. Later research showed that MinerU’s built-in VLM already supported this conversion, bringing tables and flowcharts into the same parser and model.

A controlled five-page document let me repeat the checks across the full pipeline. The linker resolved all 13 cross-page references, and the reconstructed flowchart preserved every node, edge and label and supported correct answers to both test questions. I used this evidence alongside deployment and operating-cost analysis to develop the client recommendation, including its preference to operate fewer AI models.