Full Stack AI Software Engineer

As a Mid-Level AI Engineer (Full Stack AI Software Engineer), you will design, build, and deploy end-to-end intelligent web applications and services. In this role, you will own the full feature loop: building intuitive user interfaces, developing scalable backend APIs, and integrating Generative AI capabilities—such as Large Language Model (LLM) APIs, retrieval-augmented generation (RAG) pipelines, and autonomous AI agent workflows. Working with product managers, designers, and fellow engineers, you will transform product roadmaps and customer workflows into reliable, secure, AI-powered applications.

Responsibilities:

• End-to-End AI Feature Delivery: Build, ship, and maintain AI-powered features across the entire stack, connecting modern browser interfaces, backend services, and AI runtimes.
• Modern Frontend Engineering: Develop responsive, accessible web interfaces (React, Next.js, or TypeScript) featuring real-time capabilities such as streaming LLM responses, chat components, and interactive data visualisations.
• Backend and Agent Integrations: Build robust backend services and microservices that orchestrate LLM workflows, function/tool-calling protocols (e. g., Model Context Protocol / MCP), and agentic pipelines using Python or TypeScript.
• RAG and Data Pipelines: Implement and maintain retrieval systems, vector store embeddings, document processing workflows, and standard relational database schemas (SQL/PostgreSQL).
• Security and Guardrails: Implement enterprise-grade authentication and authorisation (OAuth 2.0, JWT, RBAC), safe API boundaries, rate-limiting, and runtime guardrails to prevent prompt injections and data leaks.
• AI Evaluation and Quality: Write automated unit and integration tests while setting up evaluation pipelines to measure LLM output accuracy, latency, token usage, and regression metrics.
• Performance and Observability: Monitor full-stack application health, implement structured logging and telemetry, and optimise API and inference latency.

Requirements:

• Experience: 3-6 years of hands-on software development experience building production full-stack web applications and backend APIs.
• Frontend Skills: Proficiency in TypeScript, HTML5/CSS3, and modern frontend frameworks (React, Next.js, or equivalent) with experience handling asynchronous states and streaming data.
• Backend Skills: Strong production experience writing typed, asynchronous backend services using Python (FastAPI, Pydantic, asyncio) and/or Node.js / TypeScript.
• Applied AI and LLMs: Practical experience integrating LLM APIs (OpenAI, Anthropic Claude, or cloud providers) into user-facing software using prompt engineering, structured tool/function calling, or agent frameworks (e. g., LangChain, LangGraph, LlamaIndex, MCP).
• Databases and Data Modelling: Solid proficiency with relational databases (PostgreSQL, MySQL), SQL query design, and working knowledge of vector databases (pgvector, Pinecone, Qdrant) or caching layers (Redis).
• Security and Auth: Practical understanding of web application security, REST/GraphQL standards, OAuth 2.0 workflows, and secure token lifecycle management.
• Engineering Best Practices: Track record of writing clean, testable code, participating in peer code reviews, and using Git with automated CI/CD workflows.

Preferred Qualifications:

• Hands-on experience implementing or hosting Model Context Protocol (MCP) servers and clients.
• Production experience with cloud ecosystems (AWS, GCP, or Azure) including serverless functions, container orchestration (Docker, ECS/Kubernetes), and secrets management.
• Experience deploying on edge runtimes (e. g., Cloudflare Workers, Vercel Edge).
• Familiarity with LLM evaluation frameworks (e. g., Ragas, Braintrust, promptfoo) integrated into CI/CD pipelines.
• Background in high-growth startups, SaaS platforms, or fast-paced technical consulting environments.

Skills

FastAPI, Full-Stack, Next.js, Node.js, Python, React, TypeScript