About AI Platform
We are developing a shared AI platform for the business units of a multi-industry group in Vietnam. The platform runs on Kubernetes with LangGraph, FastAPI, and AWS Bedrock, using LangFuse for observability, and enables business teams to build and operate their own AI agents: attaching tools, loading internal documents, and orchestrating multiple agents that work together.
About the Role
The ITBA takes the business requirement (from the Business BA / BRD) and turns it into an implementable technical specification: functional and non-functional requirements, screens, APIs, and data mapping, precise enough that Dev can build directly from it and QE can write test cases directly from it.
What You’ll Do
- Document Functional Requirements (FRD) and Non-Functional Requirements (NFR); identify impacts at a high-level scope across the platform.
- Write Functional Specification Documents (FSD) covering functional and non-functional requirements plus impact assessment.
- Specify screens/flows, API input/output, and logical data mapping.
- Coordinate UAT: support the business team in running UAT and track defects through to resolution.
- Keep specifications aligned with what has actually been implemented; flag and resolve discrepancies between design and delivery.
- Work with the QC team to hand off specifications with clear, testable acceptance criteria.
Requirements
- Minimum 3-5 years as a Business Analyst / Technical BA / Product Analyst on software products, proficient with Agile on Jira and Confluence.
- Able to read APIs and OpenAPI specifications, sequence diagrams, and JSON; able to model flows in BPMN or flowcharts.
- Able to write acceptance criteria precise enough for a QE to build test cases directly from them.
- Sound understanding of permissions and multi-tenant architecture, sufficient to flag data-leakage risk when reviewing a spec.
- Working knowledge of GenAI fundamentals: how prompts influence output, how RAG works, hallucination, tool-calling, and the non-deterministic nature of model output.
- Basic SQL for independent data verification.
- Experience with web/app products
- Strong written English (technical documentation is predominantly in English).
Preferred
- Familiarity with MCP (Model Context Protocol), LangGraph, AWS Bedrock.
- Experience specifying or operating an LLM/chatbot product in production.