Fullstack Software Engineer (AI)

TL;DR

Full-stack Software Engineer (AI): Building and optimizing tools for frontier AGI safety research, including LLM evaluation libraries and monitoring systems with an accent on tooling development, data analysis, and scalable architecture. Focus on designing LLM-powered search, collaborative evaluation logging, and automating evaluation pipelines.

Company

hirify.global is building tools for frontier AGI safety research.

What you will do

• Develop core tooling for analyzing model evaluation results, including LLM-powered search and comparison views.
• Implement features for viewing and analyzing conversations with coding agents and streaming evaluation results.
• Build collaborative editing functionalities for evaluation logs that update metrics automatically.
• Automate evaluation pipelines to streamline pre-deployment model testing.
• Create LLM agents and MCP tools to automate internal software engineering and research tasks.
• Enhance Telemetry API and instrumentation for monitoring and reliability.

Requirements

• Excitement to build tools for frontier AGI safety research.
• Experience building and maintaining evaluation libraries and tools.
• Ability to monitor and control LLM traffic.

Hiring process

• Applications are reviewed on a rolling basis; early submissions are encouraged.