Get notified of more jobs like this · No spam, ever
How your CV stacks up
Upload your CV to see how well it fits this job role
?%
Job Requirements
About the CLO Azure-Native Platform
Computershare CLO Operations is transitioning its core notice reconciliation pipeline to a high-throughput, fully Azure-native enterprise application. Moving away from low-code Power Platform workflows, the new architecture replaces legacy cloud flows and desktop automation with a scalable, custom developer stack. The platform automates the intake, text extraction, business validation, and system of record write-back for over 175,000 multi-page loan notices per month (translating to ~1.75 million individual transactions). Orchestrated by Azure Durable Functions and backed by Azure Cosmos DB and Azure SQL Database, the platform features an 11-stage background pipeline, high-precision AI document extraction, an asynchronous knowledge plane, and a custom React-based Human-in-the-Loop (HITL) review surface hosted on Azure Container Apps. The platform operates under strict financial constraints: the core system of record (CDO Fusion) remains immutable, and any changes must pass through a single, secure gateway with human approval.
Reasons to use Rodeo
Start with a chat, not a search bar
Grad scheme, placement, apprenticeship? Not sure what you want yet — that's fine. Your agent talks it through with you and turns "I have no idea" into a shortlist.
It searches the market for you
Every day your agent scans the market matching roles against what actually matters to you, not just keywords on a CV.
Only hits
No noise. No "maybe this fits." Just roles with a clear explanation of why they're right — and where to focus when applying.
Key Responsibilities
- Execute High-Performance OCR: Configure and tune Azure Document Intelligence Read services to process thousands of complex document pages daily. Establish automated page-level quality and language scoring to detect low-confidence or non-English notices, routing exceptions to human remediation lanes early in the pipeline.
- Implement Cost-Optimized Classification: Maintain and scale the platform's Stage 4 document classification logic. Direct standard, recognizable document types through deterministic, rule-based routing built in Python (matching barcodes, cover-sheet keywords, and metadata) to minimize costs. Configure Document Intelligence Custom Classifiers to execute on the residual edge cases and handle multi-document bundle splitting.
- Train Semantic Extraction Models: Build, train, and manage Azure AI Document Intelligence Custom Neural models and Azure AI Content Understanding services to extract financial variables from unstructured, high-variance notices (such as LoanIQ, interest notices, and drawdowns), replacing legacy rigid template models with highly robust neural architectures.
Get help with your application
Your very own career expert that helps elevate your application to the next level.
Work Experience
10-15 Years
“It took my CV and asked me questions relevant to understanding what kind of jobs to suggest for me. Suggestions were almost perfect. Jobs were exactly what I’ve been looking for.”
Jessica, London
Location