Description

Design, Build and Optimize bedrock – powered pipelines replacing custom trained NLP and rule-based models across multiple production Lambda functions. Develop and iterate on prompts, agentic workflows, and tool-use patterns that extract transaction attributes from complex financial documents - PDFs, Excel, word and images Implement Bedrock knowledge bases to replace hardcoded business rules and fragile per-invoice API calls with managed, queryable reference data Build and maintain an evaluation harness to measure FM extraction accuracy against historical ground truth enforcing accuracy gates before any production promotion Integrate Bedrock agents with Internal APIs using tool-use patterns, replacing legacy direct, database queries Participate in parallel – run infrastructure – running old and new systems side by side in TEST, logging divergence and driving statistical validation before cutover Contribute to team knowledge transfer, this role works closely with senior AI engineers who lead FM and bedrock capability across the team Skills: Digital : Amazon Web Service(AWS) Cloud Computing~Digital : Artificial Intelligence(AI)~Data Concepts & Data Modelling~Digital : Chatbots / Conversational Agents~AI and Automation

Key Skills

Education

Bachelor's degree