Full stack application development - AI translation evaluation app

Project summary: MT Evaluation Platform We are building an AI-first web platform for machine translation quality evaluation. Users upload test data, optionally translate via an existing orchestration platform, configure checks and an LLM jury guided by AI, see a pre-run cost/token estimate, run an async evaluation job, then review quality, cost, and Human Review outcomes. In this project, we would like you to create an early version within 6 weeks and then support and upgrade it long-term. You will work with a technical product owner and a detailed specification. You will have: - a working prototype - a set of provided Python scripts - a set of components such as authentication module Stack: Python, Tailwind, PostgreSQL, TypeScript You can use coding agents Requirements: - experience with ML apps - availability for long-term - the app must be tested and functional - we will deploy in AWS