AI Fullstack Engineer

Primary Roles & Responsibilities

▸ At SDE-2 you will build, and maintain end-to-end RAG pipelines — from ingestion and chunking to retrieval and LLM response synthesis

▸ Design and develop MCP (Model Context Protocol) servers that power AI agents and multi-step workflows

▸ Development on Next.js / React.js frontend modules for our AI product suite

▸ Own PostgreSQL database design — schema modelling, indexing strategy, query optimisation, and migration management

▸ Integrate third-party AI APIs (Gemini, OpenAI, Anthropic, etc.) and open-source models into production-grade applications

▸ Work directly with Founders for product and leadership to scope features, estimate effort, and make architectural recommendations

▸ Stay ahead of the AI engineering curve — evaluate new tools, frameworks, and models and bring recommendations to the team

▸ Deep hands-on experience with RAG: multi-stage retrieval, re-ranking, hybrid search, prompt engineering

▸ Experience building or extending MCP servers — understanding of tool calling, context passing, and agent orchestration

▸ Strong proficiency in Next.js and React.js — you've built production UIs with proper state management, routing, and performance considerations

▸ PostgreSQL expertise: advanced queries, indexing, schema design for complex domains, migrations in production

▸ TypeScript proficiency — you write it by default, not as an afterthought

▸ Experience with at least one vector database (pgvector, Pinecone, Weaviate, Qdrant)

Good to Have

▸ Experience with streaming LLM responses, tool/function calling, and multi-agent frameworks

▸ Familiarity with LangChain, LlamaIndex, or custom agentic implementations

▸ Exposure to cloud infrastructure (AWS / GCP / Azure) and containerisation (Docker)

▸ Knowledge of frontend design systems, Tailwind CSS.

▸ Prior experience working directly with product or business stakeholders