Senior Fullstack Engineer (Python / React / LLM) (Experts Platform)

We are building a platform for scouting and supporting experts. Experts join through a partner network, undergo verification against criteria, sign agreements online, and fill out structured forms about their professional activities. This data is used to compile databases for our other products.

The project is currently at the MVP stage. The first experts are expected to start using the product in August 2026, with the first clients anticipated around September. The backlog for the next 6-12 months is still being formed, so tasks and priorities will be refined as the product is tested.

We are looking for two fullstack engineers: the first will join at the start and lay the architectural foundation, and the second will join shortly after.

Responsibilities

You will build the platform from scratch: from partner registration via referral link to transferring expert data to adjacent products.

1. Design the backend, API, and data structure.
2. Develop partner and expert personal accounts using React: forms, progress tracking, statuses, revision requests.
3. Build an admin panel: application queue, notifications, expert decisions.
4. Create the partner onboarding flow: video tutorials, tests, work access.
5. Manage contracts within the expert's personal account.
6. Construct a KYC pipeline using LLM: document intake, data extraction, criteria assessment, verdict.
7. Ensure LLM quality: prompt engineering, result stability, resolving discrepancies with administrator decisions.
8. Aggregate structured data from forms and provide it to adjacent products via API.
9. Build queues and background processes, deploy, and maintain stability post-release.

Tasks will be presented not as ready-made technical specifications, but as descriptions of processes and expected outcomes. Engineers will need to independently clarify constraints, compare implementation options, and choose solutions suitable for the current scale, not hypothetical future needs. Some input data processing requirements will be incomplete and will need to be clarified together with the product team and owners of adjacent products.

Team

The engineer will work directly with the Product Manager and Designer. There is currently no dedicated CTO, architect, or DevOps in the team, so the employee must make technical decisions independently and see tasks through to production.

Expansion of the technical team is planned for a later stage.

Tech Stack

Backend: Python, FastAPI, asynchronous processes, background tasks, queues, external APIs. Frontend: React. Data and Infrastructure: PostgreSQL, S3-compatible storage, Railway, Git. LLM: Anthropic API and comparable providers, structured output, document processing.

The tech stack is negotiable: engineers can propose alternative tools if they better suit the product's needs.

What's Important

1. Five or more years of commercial development experience and work at a senior level.
2. Strong Python skills and experience launching production applications.
3. FastAPI or a comparable Python framework.
4. Practical experience with LLMs in production, not just in prototypes: structured output, error handling, retries, cost control, result stability.
5. LLM pipelines: LangGraph, LangChain, RAG, or comparable tools.
6. Experience obtaining structured data from unstructured text and documents.
7. Designing APIs and data schemas.
8. Working with asynchronous operations, queues, and long-running background processes.
9. Solid knowledge of PostgreSQL: indexes, transactions, migrations, and query optimization.
10. Practical experience with React and integrating frontend with backend APIs.
11. Experience with systems involving roles and access rights: different user types seeing different data.
12. Independent application deployment and post-release diagnostics.
13. Careful handling of personal data: document storage, access controls, logging.

Experience launching a product from scratch, working in a startup or small team, and direct interaction with the product team is particularly relevant.