Senior Research Engineer (AI)

TL;DR

Senior Research Engineer (AI): Building experimental systems for mechanistic interpretability, model alignment, and steering with an accent on activation analysis and formal methods. Focus on developing foundational research tools to inspect and measure model behavior at the activation level in a highly exploratory environment.

Location: Must be based in or able to work onsite in San Francisco, CA or New York City, NY

Salary: $150,000–$400,000

Company

An early-stage AI research lab focused on interpretability, alignment, and experimental AI systems.

What you will do

• Conduct research in mechanistic interpretability and activation analysis.
• Build experimental RL environments and alignment research tools.
• Develop systems for concept detection, probing, and model steering.
• Apply formal methods, program analysis, and verification techniques to AI safety.
• Design and implement greenfield research systems from scratch.

Requirements

• Must be able to work onsite in San Francisco or New York City.
• Strong software engineering fundamentals.
• Experience building research prototypes rather than production systems.
• Ability to independently drive complex technical projects.
• Strong abstraction and systems thinking skills.
• Experience working in highly exploratory research environments.

Nice to have

• PhD in a relevant field.
• Background in programming languages and compilers.
• Experience with formal verification or theorem proving.
• Security research experience.

Culture & Benefits

• Highly competitive compensation package including equity.
• Opportunity to work on foundational AI research.
• Collaborative environment with a highly technical team.
• Focus on scientific discovery and experimentation rather than production infrastructure.