I turn complex data into clear decisions

Situation

A local Malaysian bank's auto-financing loan applications were submitted by partner officers via email with attached documents (NRIC, payslips, bank statements). Bank officers had to manually review each email, open every attachment, and key customer details into the loan origination system — a slow, error-prone process.

Approach

• Participated in client requirement gathering to scope the AI email processing solution
• Assisted in designing the Azure architecture (Document Intelligence, Logic Apps, Blob Storage, Functions)
• Contributed to building document classification, OCR/NLP data extraction, and a cross-validation engine
• Built audit trail reporting with extracted fields, mismatches, and confidence scores

Impact

Delivered a working PoC that automates document classification, data extraction, and cross-validation of customer details — enabling loan officers to focus only on exception handling. Designed to reduce processing time, manual errors, and improve approval consistency.

Situation

A healthcare client's manual process for classifying genomic variants was slow, inconsistent, and difficult to audit — creating risk for clinical governance teams reviewing hundreds of reports.

Approach

• Designed an LLM-assisted workflow using RAG to classify variants against live evidence
• Built batch pipelines generating audit-ready reports across multiple cases
• Created reconciliation tools documenting discrepancies with legacy outputs
• Translated complex outputs into summaries non-technical reviewers could act on

Impact

Improved classification consistency while cutting manual review time. Established a scalable, auditable foundation the client could extend to future report types.

Situation

SkyWorld, a leading Malaysian developer, needed a scalable way to handle multilingual customer queries and extract structured sentiment data to inform strategy. A university-industry collaboration.

Approach

• Ran stakeholder analysis to define chatbot scope and sentiment framework
• Engineered hierarchical sentiment models aligned with business classification tiers
• Designed modular FastAPI + MultiLLM architecture for multilingual support
• Trained models with Hugging Face pipelines, meeting accuracy KPIs

Impact

Delivered a working multilingual prototype with integrated sentiment analytics. Modular architecture ensured the client could maintain and extend it independently after handover.