Mechanistic Interpretability ML Expert at AfterQuery

Mechanistic Interpretability ML Expert | $150–200/hr | Worldwide Remote

AFTERQUERY is seeking a highly skilled Machine Learning Researcher with deep expertise in mechanistic interpretability for a short-term, project-based engagement. This is a rare opportunity to work at the frontier of AI safety and interpretability research, with exceptional compensation and meaningful contributions to your research portfolio.

About the Role

This is a fully remote, asynchronous contract position spanning 2–3 weeks, with an expected commitment of 10–20 hours per week for accepted projects. Work is assigned on a project-by-project basis, giving you flexibility while engaging with cutting-edge research challenges.

Key Responsibilities

• Analyze internal model representations within large language models (LLMs)
• Reverse-engineer learned circuits and computational structures within neural networks
• Develop novel tools and techniques to advance mechanistic interpretability research
• Work independently on open-ended, frontier-level research tasks

Required Qualifications

• At least one first-author publication in a peer-reviewed venue (e.g., NeurIPS, ICML, ICLR, or equivalent)
• Master's or PhD in Machine Learning, Artificial Intelligence, Computer Science, or a related quantitative field
• Demonstrated expertise in mechanistic interpretability, model analysis, or AI safety research
• Deep familiarity with transformer architectures and modern LLM internals
• Strong problem-solving ability and capacity to work independently on complex, open-ended tasks

Why Apply?

• Exceptional hourly compensation: $150–$200/hr
• Exposure to cutting-edge AI safety and interpretability research
• Flexible, asynchronous work structure
• Valuable addition to your academic and professional research portfolio