Systems Engineer – AI Coding Agent Evaluation

About the role

This position focuses on evaluating frontier AI coding agents by applying realistic systems‑engineering workflows. You will work on short, sprint‑based projects that help improve AI model performance through detailed technical assessments.

Key responsibilities

• Use AI coding agents (e.g., Cursor, Claude Code, Codex, Windsurf, Gemini CLI) to complete complex engineering tasks.
• Review model‑generated code, architecture decisions, and system implementations for correctness and efficiency.
• Identify bugs, edge cases, performance bottlenecks, and failure modes.
• Compare outputs from multiple frontier models and assess their strengths and weaknesses.
• Apply professional engineering judgment to realistic systems‑engineering scenarios.

Required profile

• 2+ years of professional systems‑engineering experience.
• Experience with distributed systems, networking, operating systems, storage systems, infrastructure software, or database internals.
• Regular use of AI coding agents and ability to evaluate model‑generated designs.
• Experience building highly scalable and performance‑critical systems is preferred.

Required skills

• Distributed systems
• Networking
• Operating systems
• Storage systems
• Infrastructure software
• Database internals
• Cursor
• Claude Code
• Codex
• Windsurf
• Gemini CLI

What we offer

• Compensation of $400 per accepted task (typical tasks take 1–3 hours after ramp‑up).
• Flexible sprint‑based schedule with 12–24 hour project windows.
• Opportunity to influence the development of cutting‑edge AI coding models.