Full-Stack Engineer (AI & Product)

About the role

We are looking for a Full‑Stack Engineer who treats AI as a core component of the modern tech stack. As an early member of the engineering team you will bridge robust software architecture with cutting‑edge machine learning to deliver seamless user experiences.

Key responsibilities

• Design, develop and maintain scalable web applications using Next.js, Node.js, Python, FastAPI, Docker and PostgreSQL.
• Integrate and optimise LLM‑powered features with frameworks such as LangChain or LlamaIndex, manage vector databases and handle prompt engineering.
• Own end‑to‑end feature delivery from concept through production‑ready deployment, including performance tuning for high‑traffic interfaces and computationally intensive AI inference.
• Collaborate closely with product and design teams to ensure AI features are intuitive, ethical and solve real user pain points.

Required profile

• Expert‑level proficiency in Next.js with a strong focus on state management, component reusability and fast UX.
• Solid experience building backend services with Node.js, Python (FastAPI) or Go, and familiarity with RESTful APIs and GraphQL.
• Hands‑on experience with OpenAI, Anthropic or open‑source LLMs (Llama, Mistral) and a good grasp of prompt engineering, RAG and model fine‑tuning.
• Comfort with cloud platforms (AWS, GCP or Azure), Docker and CI/CD pipelines.

Required skills

• Next.js
• Node.js
• Python
• FastAPI
• PostgreSQL
• Docker
• LangChain
• OpenAI API
• Anthropic API
• LLM integration (prompt engineering, RAG)
• Cloud platforms (AWS, GCP, Azure)