Research Intern: Interpretability & Reliability (Summer 2027)
About the role
Research internship focused on interpretability and reliability for frontier AI models, with hands-on ownership of a real research problem and collaboration with CTGT’s Policy Engine team in San Francisco.
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
Qualifications
- 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
- Ability to 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 track record that shows 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
Skills
Benefits
- World-Class Backing: You will join a venture-backed company with institutional investors including Google's Gradient Ventures, General Catalyst, and Y Combinator
- Real Impact: You will work directly on core systems that determine model performance in high-stakes environments
- Autonomy & Trust: High degree of trust; opportunity to form strong technical opinions and execute them
About CTGT
CTGT safeguards against reputational risk from GenAI across your org
Enterprises are paralyzed by the risks of deploying generative AI. Traditional methods like RAG and fine-tuning are brittle, expensive, and fail to prevent costly hallucinations or guarantee compliance in high-stakes environments. This lack of trust stalls innovation and blocks ROI. CTGT ensures strict, auditable adherence to your policies on the fly. We deliver defensible audit trails and remediate noncompliant model behavior, so outputs become more aligned with company policies over time, combating data and model drift. CTGT is backed by Google's AI fund (Gradient), General Catalyst, and luminaries like Paul Graham. We provide the control and confidence necessary to unlock the full potential of enterprise AI.
More open roles at CTGT
- Software Engineering Intern (Summer 2027)3mo agoSan Francisco, CA
- Senior Software Engineer, Product5mo agoHybrid (San Francisco, CA)
- Senior Software Engineer5mo agoHybrid (San Francisco, CA)
- Senior Software Engineer, Platform5mo agoSan Francisco
- Machine Learning Engineer: LLM Interpretability & Systems7mo agoHybrid (San Francisco, CA) · Engineering