FluidLabs

About the Role

We are building an agentic document-processing platform that autonomously extracts, validates, and routes financial documents through complex approval workflows - without manual intervention. The system combines LLM orchestration, MCP (Model Context Protocol) servers, and enterprise API integrations into a single AI-driven pipeline.

We are looking for a Junior Full-Stack Developer to join a small senior team. You will work on real features - backend services, frontend components, database queries - and gain structured mentorship on a production AI product. No prior AI or LLM experience required.

This is a learning role with clear growth expectations. Within 12–18 months, you are expected to reach an independent Mid-level engineer on the full stack, including the AI orchestration layer.

Core: JavaScript/TypeScript (async, basic OOP), React (hooks, components), SQL (queries + indexes), Git, HTTP/REST, English B1+.

Plus: any backend framework (NestJS/FastAPI), deeper TypeScript, Docker, PostgreSQL; bonus/growth — LLM APIs, MCP/agents, React Query/Zustand, OpenTelemetry.

What You’ll Work On

Backend Development

• Build and maintain REST API endpoints using NestJS (Node.js / TypeScript) or FastAPI (Python)
• Write and optimize PostgreSQL queries, design simple schema additions, run migrations
• Add unit and integration tests; fix bugs identified in code review
• Integrate third-party REST APIs under senior guidance

Frontend Development

• Build React 18 + TypeScript components for document dashboards and approval workflows
• Connect UI to live backend APIs; replace mock data, handle loading and error states
• Work with Tailwind CSS and shadcn/ui component library
• Implement real-time status updates via Server-Sent Events (SSE)

AI Components (Mentored)

• Learn how the MCP server works: tools, context management, structured outputs
• Make calls to LLM APIs (OpenAI, Anthropic) using existing patterns; extend prompt templates
• Understand document extraction pipeline and help build UI for reviewing AI decisions
• Gradually take on AI-adjacent tasks as confidence grows

Infrastructure & Quality

• Work with Docker and docker-compose for local development
• Create and update GitHub Actions workflows for simple CI tasks

• Follow code review feedback and improve over time
   

   

What We’re Looking For

Beyond technical foundation, these qualities define the right person for this role:

Coachability

You take feedback seriously, apply it, and don’t repeat the same mistake twice. Code review is a learning tool, not criticism.

Curiosity

You investigate before asking. When you don’t know something, you try first, document what you tried, and then ask a specific question.

Ownership

You don’t drop tasks because they got unclear. You ask the right question, unblock yourself, and follow through to done.

Honest communication.

You say “I don’t know” when you don’t know. You flag blockers early rather than going silent for days. Async first -written updates matter.

We're building an AI-powered document processing platform that automates complex back-office workflows — from intake and validation to approval and ERP synchronisation. The system is already in production and handles real financial flows; you'll be joining at the scaling stage.

What you'll work on

• AI orchestration layer: LLM tool-calling pipelines (Claude / OpenAI), MCP server (4 domain tools), context and retry management
• Integrations: Microsoft 365 Graph API, DocuSign REST API, Azure Document Intelligence
• Validation & routing engine: business rules, confidence scoring, exception handling
• Backend API: REST + SSE, OAuth2/OIDC, audit logs, OpenTelemetry
• Frontend: React 18 + TypeScript + Tailwind dashboard (agent status, approval queue, analytics)
• Infrastructure: Docker, GitHub Actions CI/CD, Azure / AWS cloud

Required

• Node.js + TypeScript — 4+ years in production, architecture-level decisions
• LLM API integration — tool calling, prompt design, context management (OpenAI, Anthropic, or Gemini)
• REST API design + OAuth2/OIDC implementation
• PostgreSQL — schema design, query optimisation, migrations
• Microsoft 365 Graph API or similar enterprise API (SharePoint, OneDrive, Teams)
• Azure Document Intelligence / AWS Textract / similar document AI service
• React 18 + TypeScript — you can own the frontend when needed
• Docker + CI/CD (GitHub Actions or equivalent)
• Cloud deployment (Azure or AWS)
   

Nice to have

• DocuSign API experience
• MCP (Model Context Protocol) — building or consuming MCP servers
• pgvector / vector similarity for deduplication
• OpenTelemetry — metrics, traces, structured logs
• Tailwind CSS + shadcn/ui
   

We're looking for

Someone who has shipped AI-integrated features in production — not just experimented with them. You take ownership end-to-end: design → implementation → deployment → monitoring. You can make pragmatic architecture calls and explain trade-offs clearly.
 

Senior bar: you've led technical design of at least one non-trivial integration (enterprise API, document pipeline, or payment flow), and you don't need to be told what to research.
 

Offer

• Fully remote, async-friendly, EU time zone overlap (11:00–19:00 Kyiv)
• Small product team no bureaucracy, direct access to founders
• 24 days paid leave + public holidays
• 3-month probation period
   

How to apply

Apply via Djinni or send your CV + a short note about your LLM integration experience. Тell us: what was the most complex API integration you