Fullstack AI Engineer (LLM + Agentic Systems)

• Contract

• Rates Negotiable

• Fully Remote

We’re looking for a Fullstack AI Engineer to build and scale AI-powered features inside modern web applications. This is a hands-on role for someone who enjoys shipping real product, working across the stack, and turning LLM capabilities into secure, reliable systems.

Your Direct Impact

• Build production features using LLMs, embeddings, RAG, and agentic workflows
• Implement orchestration with tools like LangChain, LangGraph, Smolagents, or Vercel AI SDK
• Develop backend services in TypeScript, Python, or Go
• Build modern UI experiences in React
• Design secure, scalable APIs and real-time systems (FastAPI, WebSockets, SSE)
• Deploy and scale services on GCP and/or Azure using Docker, Kubernetes, Terraform
• Work with SQL + NoSQL, plus vector databases (Milvus/Qdrant) and graph databases (Neo4j/FalconDB)
• Improve production performance + cost using caching, batching, quantization, and model routing
• Add evaluation + observability using LangSmith, W&B, Prometheus, Grafana, OpenTelemetry
• Help adopt emerging standards like Model Context Protocol (MCP) (or equivalent)

What you will Bring

• Proven experience integrating LLMs + embedding models into real applications
• Strong fullstack engineering (backend + React)
• Cloud and infrastructure experience (GCP/Azure, Docker/K8s, Terraform)
• Solid engineering fundamentals: clean code, testing, CI/CD, maintainable architecture
• Strong communication skills with technical and non-technical stakeholders