Research Intern: Interpretability & Reliability (Summer 2027)

Summary

CTGT is a venture-backed company focused on AI governance, born out of Stanford University research. They are seeking a Research Intern to tackle complex problems in machine learning interpretability and reliability, working directly with engineers on real research questions and contributing to the development of the Policy Engine.

Responsibilities

• Implement and stress-test methods for feature extraction and runtime intervention, from control vectors to activation probes, and make them work repeatably across model families
• Design evaluations that bound error rather than average it: calibration under imbalanced data, reasoning-trace grading, behavior in verifiable and non-verifiable task regimes
• Read the relevant literature, decide what actually matters, reproduce it, and push past it
• Work with engineering to turn a finding into a Policy Engine capability that ships into audited, high-stakes environments
• Present your progress every week and defend your reasoning

Skills

• Pursuing a degree (Bachelor's through PhD) in computer science, mathematics, the sciences, or a similarly unforgiving quantitative field
• Strong mathematical foundations: linear algebra, probability, optimization, information theory
• Can read a paper, decide what matters, and implement it
• Have written real code for real computational systems; fluency with PyTorch and the modern ML stack, or the track record that says you will have it in weeks
• Drawn to interpretability, model internals, and making systems provably reliable rather than usually fine
• Self-directed, and able to make real progress without constant scaffolding

Qualifications

Must Haves

• Pursuing a degree (Bachelor's through PhD) in computer science, mathematics, the sciences, or a similarly unforgiving quantitative field
• Strong mathematical foundations: linear algebra, probability, optimization, information theory
• Can read a paper, decide what matters, and implement it
• Have written real code for real computational systems; fluency with PyTorch and the modern ML stack, or the track record that says you will have it in weeks
• Drawn to interpretability, model internals, and making systems provably reliable rather than usually fine
• Self-directed, and able to make real progress without constant scaffolding

Benefits

• We sponsor US visas
• You will join a venture-backed company with institutional investors including Google's Gradient Ventures, General Catalyst, and Y Combinator
• You will work directly on the core systems that determine how models perform in the wild. Your work ships into real, high-stakes environments where governance, auditability, and performance are non-negotiable
• We operate with a high degree of trust. You are expected to form strong technical opinions and execute on them