Mad Devs is looking for a Junior Agentic Developer to help improve the technical health of internal engineering projects using AI-powered development workflows and our internal platform, Enji Guard.
What You Will Do
- work on internal Mad Devs projects and engineering tools
- investigate engineering issues identified by Enji Guard
- analyze unfamiliar codebases and understand existing technical constraints
- use AI coding agents to implement improvements
- review, test, refactor, and debug AI-generated code
- improve code quality, reliability, maintainability, documentation, testing, CI/CD, and production readiness
- prepare and merge pull requests
- collaborate with mentors and engineering teams through code reviews, technical discussions, and feedback sessions.
The goal is not simply to generate code with AI. The goal is to improve real software systems and make them healthier, more reliable, and easier to maintain.
Requirements
- 6+ months of commercial software development or equivalent hands-on experience demonstrated through personal, freelance, academic, or open-source projects
- experience using AI coding agents (such as Codex, Claude Code, Cursor, GitHub Copilot, or similar tools) in at least one substantial software project
- experience with at least one of the following programming languages: Python, JavaScript/TypeScript, or C++
- working knowledge of Git and pull requests
- basic experience working with Linux, Docker, and relational databases such as PostgreSQL
- familiarity with software quality practices, including testing, debugging, refactoring, and writing maintainable code;
- basic understanding of CI/CD concepts and modern software development workflows
- the ability to clearly explain: what the AI generated, what decisions you made, etc.
- English at B2-C1 level, Russian at B2 level
Nice To Have
- open-source contributions
- experience with CI/CD pipelines
- a GitHub, GitLab repository, or another project that demonstrates your work
- deployed public projects
- experience fixing bugs in unfamiliar codebases
- hackathon, bootcamp, or competitive programming achievements
- your own product, startup, automation, or tool that creates measurable value.
How To Apply
In addition to the traditional CV send us a short proof-based application with:
- links to your GitHub or GitLab projects built with AI agents
- a short explanation of what each project does
- which AI tools you used and how you used them
- what parts were generated by agents
- what parts you personally designed, reviewed, fixed, tested, or improved
- examples of tests, CI/CD, deployments, users, or real-world usage if available.
Also include a short mini-essay:
“Describe the most difficult problem you face now in 10 sentences.”
We are not looking for perfect resumes. We are looking for people who can show real work, clear thinking, persistence, and the ability to use AI agents to improve real software.