About the Role

You will build and improve AI agents that work directly on our production code.

Your main job is to build a specialized AI agent that understands our codebase and helps make it faster, cleaner, simpler, and cheaper to maintain.

This is hands-on work on real code and real problems.

How We Work

• Business impact first: Cheaper, Faster, and Better
• Simple beats complex
• Small changes, shipped fast
• You own your work end to end
• First question is always: do we even need this
• Flat team, no micromanagement
• Decisions can change tomorrow. Adaptability matters.
• No long PRDs One clear goal, discuss, execute
• We ship fast, measure, and improve

Not for You If

• You need detailed instructions
• You dislike ambiguity
• You prefer complex solutions over simple ones
• You do not want to touch Linux or infrastructure
• You just want a safe 9 to 5

What You Will Do

• Use AI agents to optimize, refactor, and remove code
• Feed logs and performance data back into the agent
• Profile applications and find bottlenecks
• Optimize SQL queries and database usage
• Improve deployments and release processes
• Continuously improve internal AI tooling

Tech You Should Be Comfortable With

You do not need to be an expert in everything, but you should be comfortable working with:

• Linux CLI (Required)
• Python
• PHP
• SQL (MySQL or MariaDB)
• Shell scripting
• LLMs

What We Are Looking For

• 1+ year of software engineering experience (new graduates are welcome)
• Strong understanding of performance optimization
• Experience cleaning up legacy or messy codebases
• Practical profiling and debugging skills
• Comfortable working close to infrastructure and deployments
• Thinks in terms of automation
• Can explain technical decisions clearly and simply in English

Nice to Have

• Experience building AI agents
• Experience with large or long-running systems
• CI/CD or deployment automation experience