Full Stack Developer

Magellan AI•New York, NY

7d•$100,000 - $140,000•Remote

About The Position

Magellan AI is seeking an experienced full-stack developer to join their team of seven engineers. This role will focus on launching a major new feature and enhancing the core product. The company utilizes AI agents (Claude Code and Codex) for code drafting under close supervision, emphasizing the importance of precise problem specification and solution evaluation over typing speed. The developer will be responsible for adding new features to the Ruby on Rails application, directing AI coding agents, improving system/code quality through practices like TDD and refactoring, documenting designs and architecture, extending internal tooling, building AI-facing product surfaces, enhancing front-end usability with Turbo/Stimulus, troubleshooting performance issues in Postgres and ClickHouse, providing stopgap solutions, sharing operational support, and experimenting through internal hackathons.

Requirements

3+ years of software development experience
Expertise with Agile web development, with practices such as TDD and Refactoring
Fluency working with AI coding agents day to day, or the obvious appetite for it.
Clear writing. You will be writing specs, ADRs and documentation read by people who are not engineers.

Nice To Haves

Ruby on Rails
ClickHouse
Python
NYC-based
Experience designing MCP servers or other LLM-facing APIs
Background in ad tech
Interest in the podcasting world

Responsibilities

Adding new features to our Ruby on Rails application from top-to-bottom, full stack.
Directing AI coding agents through real work: framing the problem and its constraints, reviewing what comes back line by line, pushing back when a solution has outgrown the problem, and starting over simpler when that is the right call.
Increasing system/code quality by using practices such as TDD and refactoring.
Writing the design down before the code: specs, architecture decision records, and product documentation for our operations team.
Extending our own tooling — the skills, subagents and CLI helpers that encode how we work.
Building AI-facing product surfaces, like our Ad Intelligence MCP server, where the consumer of the API you design is a language model rather than a browser — with the authentication, policy gates and audit logging that implies.
Enhancing usability of existing features via Turbo/Stimulus and other front-end improvements.
Troubleshooting and fixing performance issues and complicated logic across Postgres and ClickHouse.
Experimenting and providing stopgap solutions for potential opportunities.
Sharing in providing operational support to make sure the system stays running and address any bugs.
Experimenting via internal hackathons to produce novel solutions and feature enhancements.