AI Business Analyst Intern
Genesis Networks Pte Ltd
- Streamlined early delivery workflows with an internal AI "document engine" that turns one client brief into research summaries, proposals, functional specs, and test cases, cutting first-draft time from a week to an hour (98%)
- Re-architected the engine from no-code n8n workflows into modular Python FastAPI services exposed to an LLM agent as callable tools over the Model Context Protocol (MCP), plus a custom chat interface
- Engineered the retrieval (RAG) layer in Python: embedded documents through a self-hosted TEI service, stored vectors in PostgreSQL with pg-vector, and ranked context by cosine similarity
- Established a fully in-cluster deployment path with Docker, Jenkins CI, and Kubernetes (Rancher) against a self-hosted LLM with no public endpoints, alongside private MinIO object storage
- Validated the pipeline end-to-end on a sample client scenario: 22/22 functional requirements covered and 51 test cases generated, with bidirectional FR-ID coverage and no orphans
- Translated business requirements into technical implementation across the SDLC, working hands-on with GitLab and Claude Code
Stack
- FastAPI
- MCP
- PostgreSQL
- pg-vector
- TEI
- RAG
- Docker
- Kubernetes / Rancher
- Jenkins
- n8n
- MinIO
- GitLab
- Claude Code