Full Stack Engineer

We are looking for a sharp, systems-minded engineer who wants to work at the intersection of AI tooling and production software engineering. You will work directly with leadership to architect multi-system workflows, build agentic pipelines, write production code across multiple stacks, and operate as a force multiplier for the engineering org. This role spans multiple active product initiatives: an AI-powered intelligence platform, customer analytics and data products, subscription and billing automation, and internal tooling that makes the entire team more effective. The common thread is that you will use AI-assisted development as your primary working method, and you will build the systems that make that method scale.

This is not a prompt engineering role and not a research role. You will ship production code daily. You will write technical specifications that AI systems and humans can both execute from. You will review AI-generated code with the same rigour you would apply to any pull request. And you will build the context management systems, evaluation frameworks, and integration pipelines that make all of this work. We are hiring for potential, not for a title that already exists. If you have strong full-stack fundamentals, you use AI tools as a real part of your daily workflow, and you are hungry to grow into a role that barely existed two years ago, keep reading.

Responsibilities:

• Write production code daily across TypeScript/React, Node.js/Express, Python, SQL, and serverless functions.
• Write precise technical specifications and build guides before touching code. Spec quality is how we measure engineering maturity here.
• Architect and build agentic AI workflows that span multiple systems, APIs, and data sources.
• Review and validate AI-generated code for correctness, security, and consistency with existing codebase patterns.
• Build integration pipelines that connect CRM, billing, contract management, onboarding, dispatch, and analytics systems.
• Design and maintain AI skills, context pipelines, and evaluation frameworks that improve the quality of AI-assisted output over time.
• Own context management: handoff documents, session summaries, project knowledge bases that keep AI tools effective across sessions.
• Debug cross-system issues that span multiple services, databases, and external APIs.
• Collaborate directly with leadership to translate business requirements into system designs and shipped features.

Requirements:

• Everything else you will learn on the job. Strong proficiency in TypeScript/JavaScript (React, Node.js, Express) with production experience.
• Working proficiency in Python for scripting, data pipelines, automation, and tooling.
• Solid SQL and relational database skills (PostgreSQL, understanding of indexes, joins, and query optimisation).
• Experience building and consuming RESTful APIs and working with event-driven patterns.
• Hands-on, daily use of AI coding tools (Claude, Cursor, Copilot, or similar) as a real part of your development workflow.
• You should be able to talk about what works, what doesn't, and how you validate the output.
• Ability to read and contribute to codebases you did not write, across multiple languages and frameworks.
• Understanding of security fundamentals: input validation, secrets management, parameterised queries.
• Experience with git workflows, branching strategies, and pull request reviews.

Nice to Have:

• Experience with Supabase, serverless functions, or edge computing platforms.
• Familiarity with Docker, CI/CD pipelines, and cloud deployment.
• Experience with workflow orchestration tools (n8n, Temporal, Airflow, or similar).
• Familiarity with LLM APIs, tool-use patterns, and multi-agent design.
• Experience building evaluation frameworks or quality benchmarks for AI-generated output.
• 2-5 years of professional software engineering experience.
• Has shipped features across the full stack (frontend + backend + database) in a professional setting.
• Has worked in an environment where detailed instructions were not always available.
• Startup, small team, or a role where you had to figure things out.
• Has used AI tools as part of a real development workflow, not just experimented.
• Can speak to what works, what fails, and how you verify output.
• Can write technical documentation that another engineer can pick up and execute from without a walkthrough.