Full-Stack Engineer (AI & Product)

About the role

We aren't just looking for someone to move data from a database to a UI. We are looking for a Full-Stack Engineer who views AI as a core component of the modern tech stack, not just a buzzword. As an early member of our engineering team, you will bridge the gap between robust software architecture and cutting‑edge machine learning.

Key responsibilities

• Architect & Build: Design and maintain scalable web applications using Next.js, Node.js, Python, FastAPI, LiteLLM, OCR, Docker, WorkOS, PostgreSQL.
• AI Integration: Implement and optimise LLM‑powered features with LangChain or LlamaIndex and manage vector databases.
• End‑to‑End Ownership: Take features from concept and prompt engineering to production‑ready deployments.
• Performance & Scaling: Optimise performance for high‑traffic interfaces and computationally expensive AI inferences.
• Collaborate: Work closely with product and design to ensure AI features are intuitive, ethical and solve user pain points.

Required profile

• Frontend: Expert‑level proficiency in Next.js, with focus on state management, component reusability and snappy UX.
• Backend: Strong experience with Node.js, Python (FastAPI) or Go, and knowledge of RESTful APIs and GraphQL.
• AI/ML Experience: Hands‑on experience with OpenAI API, Anthropic or open‑source models (Llama, Mistral) and understanding of prompt engineering, RAG and fine‑tuning.
• Infrastructure: Familiarity with AWS/GCP/Azure, Docker and CI/CD pipelines.

Required skills

• Next.js
• Node.js
• Python
• FastAPI
• LiteLLM
• OCR
• Docker
• WorkOS
• PostgreSQL
• LangChain
• LlamaIndex
• OpenAI API
• Anthropic
• Llama
• Mistral
• Prompt Engineering
• RAG
• AWS
• GCP
• Azure
• CI/CD pipelines