AI Systems Engineer: Frontier Model Evaluator

Obsidian; New York (NY); On-site; USD 180,000 - 220,000; Full time

Job summary

Obsidian is seeking contributors for a project with a leading AI research lab. The role involves using frontier AI coding agents to finalize and assess complex engineering tasks.

Contributors will review code, identify bugs, and compare outputs from different models. Strong systems engineering experience is essential, coupled with familiarity with AI coding tools. Compensation is $400 per accepted task, with typical tasks lasting 2–3 hours.

Qualifications

• 2+ years of professional systems engineering experience.
• Regular use of AI coding agents.
• Ability to evaluate model-generated systems designs.

Responsibilities

• Complete and evaluate complex engineering tasks using AI tools.
• Review model-generated code and architectures.
• Identify bugs and performance bottlenecks.
• Compare outputs from multiple models.

Skills

Systems engineering experience

Experience with distributed systems

Networking knowledge

Familiarity with AI coding agents

Scalable systems design

Tools

Cursor

Claude Code

Codex

Windsurf

Gemini CLI

Job description

Obsidian is seeking contributors for a project with a leading AI research lab. The role involves using frontier AI coding agents to finalize and assess complex engineering tasks.

Contributors will review code, identify bugs, and compare outputs from different models. Strong systems engineering experience is essential, coupled with familiarity with AI coding tools. Compensation is $400 per accepted task, with typical tasks lasting 2–3 hours.