Full Stack AI Developer (Contract)

Full-time freelance

• 2 months
• Extendable month to month

We build full-stack applications where the core logic is an LLM workflow or an agent. You will build them end to end: the interface people use, the backend that orchestrates the models, and the engineering that makes the whole thing reliable enough to put in front of a client.

What you'll own

• Complete application builds. From first prototype to deployable product, across frontend, API, orchestration, data and deployment.
• Agentic backends in LangGraph. Graph design, state management, tool calling, branching, retries, checkpointing, and human-in-the-loop interrupts where a person needs to approve what the agent is about to do.
• Frontends designed for AI. Streaming responses, visible intermediate steps, graceful handling of slow or partial failures, and controls that let users correct or approve model output. A twenty-second spinner is a broken product.
• Making model behaviour dependable. Validated structured outputs, fallbacks, guardrails, and evals that tell you whether a change actually made things better.
• Connecting to the real world. Third-party APIs, databases, documents and internal systems, with authentication and permissions handled properly.
• Fast, visible iteration. Short cycles with working demos, and the judgement to suggest a smaller scope when the original one won't ship in time.

What we're looking for

• Full-stack apps you have shipped with an LLM at the core. Send us links or repositories. We want to see something that does more than wrap a chat box around an API call.
• Hands-on LangGraph experience, in Python or JavaScript. You can explain how state moves through your graph, what happens when a node fails halfway through, and how you resume a run.
• Solid frontend engineering. React (including Next.js) with TypeScript, or Flutter, including streaming interfaces and real-time updates.
• Solid backend engineering. Python or TypeScript/Node, a relational database such as Postgres, authentication, and asynchronous processing.
• A working command of LLM fundamentals. How context windows and token costs shape design; structured output and tool calling; RAG and when it isn't the answer; choosing between reasoning and instruct models, or large and small ones, on cost and latency; why prompt injection is solved with permissions rather than prompts; and how to evaluate output that is never quite the same twice.
• Comfort with ambiguity and pace. Requirements will move. You should be able to keep shipping while they do.

Signals that would move you to the top of the list

• MCP experience, whether building servers or wiring agents to consume them.
• Observability and evals in practice. LangSmith, Langfuse or your own tracing, and a test set you actually run.
• Multi-provider work. OpenAI, Anthropic, Gemini or open-weight models, with routing and fallback between them.
• Retrieval done well. Vector stores such as pgvector or Qdrant, hybrid search, reranking, and retrieval quality you have measured.
• Deployment ownership. Docker, a cloud platform and CI/CD, so a build can go live without a separate handoff.
• Product sense. You are comfortable talking to clients and users, and you push back when a feature is expensive to build and unlikely to matter.

What this role is notIt is not research, and you will not be training models. It is not prompt engineering in a notebook. It is not frontend-only or backend-only work either. You will own both halves of applications that real people use, with the model treated as one unreliable component among many.