AI & Full-Stack Developer

About the role

We are looking for an experienced AI‑focused Full‑Stack Developer to design, build, and deploy intelligent web applications. You will blend traditional full‑stack engineering with cutting‑edge AI capabilities, turning business workflows into fast, scalable, AI‑powered solutions.

Key responsibilities

• Integrate LLMs such as OpenAI GPT‑4o and Anthropic Claude via APIs.
• Build Retrieval‑Augmented Generation (RAG) pipelines and autonomous AI agents using LangChain, LlamaIndex, or CrewAI.
• Design and query relational databases (PostgreSQL, MySQL) and vector stores (Pinecone, Qdrant, Supabase pgvector).
• Develop responsive front‑end interfaces with React, Next.js, or Vue and robust back‑end APIs using Python (FastAPI/Django) or TypeScript/Node.js.
• Apply prompt‑engineering techniques, monitor model latency and API costs, and optimise database performance.
• Participate in daily stand‑ups, maintain clean Git workflows, write unit tests, and report progress via Slack and Jira/Asana.

Required profile

• Minimum 4 years of software engineering experience.
• At least 1.5 years of hands‑on work with production AI/LLM applications.
• Strong understanding of prompt engineering, function calling, and agentic loops.
• Experience working in an agile, remote‑first environment.

Required skills

• Python (FastAPI, Django)
• TypeScript / Node.js
• React, Next.js, Vue.js
• PostgreSQL, MySQL
• Pinecone, Qdrant, Supabase pgvector
• LangChain, LlamaIndex, CrewAI
• OpenAI GPT‑4o, Anthropic Claude
• Git, Docker, AWS, GCP, Vercel