Frontier ML Engineer: Benchmark AI Coding Models

Obsidian; New York (NY); On-site; USD 207,000 - 303,000; Part time

Job summary

Obsidian is seeking contributors to support a Frontier Code Agents project with focus on realistic ML engineering workflows and model evaluation. You will analyze model-generated code, assess training and deployment considerations, and identify issues across multiple frontier models.

Applicants should have 2+ years in ML engineering, experience deploying production ML systems, and familiarity with AI coding agents such as Cursor, Claude Code, Codex, Windsurf, or Gemini CLI.

Qualifications

• 2+ years of professional machine learning engineering experience.
• Experience building production ML systems, deployment infra, or AI-powered products.
• Regular use of AI coding agents such as Cursor, Claude Code, Codex, Windsurf, Gemini CLI.
• Ability to evaluate model-generated ML implementations and tradeoffs.
• Experience deploying ML systems to production is preferred.

Responsibilities

• Use frontier AI coding agents to complete and evaluate complex ML tasks.
• Review model-generated implementations involving training, inference, and MLOps.
• Identify bugs, edge cases, performance issues, and failure modes.
• Compare outputs from multiple frontier models and assess strengths and weaknesses.
• Apply professional engineering judgment to realistic ML scenarios.

Skills

ML engineering

Production ML systems

AI coding agents

ML model evaluation

Tools

Cursor

Claude Code

Codex

Windsurf

Gemini CLI

Job description

Obsidian is seeking contributors to support a Frontier Code Agents project with focus on realistic ML engineering workflows and model evaluation. You will analyze model-generated code, assess training and deployment considerations, and identify issues across multiple frontier models.

Applicants should have 2+ years in ML engineering, experience deploying production ML systems, and familiarity with AI coding agents such as Cursor, Claude Code, Codex, Windsurf, or Gemini CLI.