Frontier ML Engineer: AI Coding Agent Evaluator

Obsidian; New York (NY); Hybrid; USD 275,520 - 826,560; Part time

Job summary

Obsidian is seeking contributors for a Frontier Code Agents project focused on evaluating and improving AI coding models. Candidates will complete and assess complex machine learning and AI engineering tasks.

The role requires at least 2 years of experience in machine learning engineering, knowledge of AI coding agents, and technical evaluation skills. Compensation is performance-based at $400 per accepted task.

Qualifications

• 2+ years of professional machine learning engineering experience.
• Experience building production ML systems and applications.
• Ability to evaluate model-generated implementations.

Responsibilities

• Use frontier AI coding agents to complete complex ML tasks.
• Identify bugs, edge cases, performance issues, and failure modes.
• Compare outputs from multiple models to assess strengths.

Skills

Machine learning engineering

AI coding agents

Model evaluation

Production ML systems

Tools

Cursor

Claude Code

Codex

Windsurf

Gemini CLI

Job description

Obsidian is seeking contributors for a Frontier Code Agents project focused on evaluating and improving AI coding models. Candidates will complete and assess complex machine learning and AI engineering tasks.

The role requires at least 2 years of experience in machine learning engineering, knowledge of AI coding agents, and technical evaluation skills. Compensation is performance-based at $400 per accepted task.