Full-stack Engineer / Agentic Coding Tools
ToptalJob Description
Summary:
We are looking for a Full-stack Engineer with strong experience using agentic coding tools to accelerate software delivery. This role is ideal for engineers who are highly productive with tools such as Claude Code and understand how to structure workflows using hooks, subagents, skills, prompts, and automation.
General Information:
The engineer will work across frontend, backend, and developer workflows, using agentic coding tools as part of day-to-day development. The ideal candidate is a strong full-stack engineer first, with deep practical experience applying AI coding assistants to build, refactor, test, and maintain production software.
Tasks and deliverables:
Build and maintain full-stack applications across frontend, backend, APIs, and data layers.
Use agentic coding tools to improve implementation speed, code quality, testing, and documentation.
Set up and manage workflows using Claude Code or similar tools.
Create and use hooks, subagents, skills, custom instructions, and reusable coding workflows.
Refactor existing codebases with the support of AI coding agents.
Write tests, review generated code, and ensure production-quality engineering standards.
Collaborate with teams to define best practices for AI-assisted software development.
Required Experience:
Strong full-stack engineering experience with modern frontend and backend technologies.
Hands-on experience using Claude Code or similar agentic coding tools in real development work.
Experience with hooks, subagents, skills, custom prompts, and structured agent workflows.
Ability to guide AI coding tools effectively while maintaining ownership of code quality.
Strong understanding of testing, debugging, code review, architecture, and maintainability.
Experience working with existing codebas
Listed via
Findwork
findwork.dev
Similar roles
Design & Tech
Related reads from TCHNX

Algorithmic Bias in Design Systems: Why Your AI-Generated UI Might Exclude Users
As AI tools increasingly generate interface components, they're embedding biases that systematically exclude users. Understanding how machine learning models inherit prejudice is essential for creating truly inclusive design systems.

The Synthetic Design Problem: Can AI-Generated Assets Ever Replace Human Creativity?
As AI design tools flood creative workflows, a fundamental question emerges: are we automating creativity or merely industrialising pastiche? The answer reshapes how we understand design innovation itself.
