Research Engineer (AI)

TL;DR

Research Engineer (AI): Building experimental systems and custom tooling for model interpretability and alignment with an accent on activation-level inspection and representation engineering. Focus on developing underlying mechanisms of intelligence and operating in an open-ended research environment.

Location: Fully onsite in San Francisco, CA

Salary: $200,000–$300,000 base + equity

Company

An early-stage AI research lab founded by former OpenAI and Google researchers dedicated to understanding the internal mechanisms of AI models.

What you will do

• Build experimental systems and research tooling from scratch to inspect and steer model behavior.
• Develop techniques for interpretability, alignment, and representation engineering.
• Work directly with model internals to measure and analyze how models reason and learn.
• Collaborate with researchers to design and implement infrastructure for mechanistic AI research.
• Maintain high standards of software engineering while operating in an open-ended research environment.

Requirements

• Strong software engineering fundamentals with experience building complex technical systems.
• Experience working on experimental ML systems, research tooling, or model-adjacent infrastructure.
• Genuine interest in interpretability, alignment, or reinforcement learning.
• Comfort working close to model internals and building custom tools.
• Must be based in San Francisco for this fully onsite role.

Nice to have

• PhD in a relevant field.
• Prior experience in research-driven environments.