Research Intern: Interpretability & Reliability (Summer 2027)

CTGT
San Francisco
Workplace: OnsiteFull timeUSD 8,000 - 12,000 annuallyFunction: Research & Scientific (R&D)Skills: ["Problem-solving","Communication","Critical thinking","Collaboration","Self-direction"]

Join CTGT as a research intern to tackle a core problem in model interpretability and reliability. You will design, implement, and evaluate methods for feature extraction and runtime intervention across model families, collaborate with engineers to ship a Policy Engine capability, and present weekly progress while contributing to high-stakes AI governance research.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
CTGT
CTGT
2 months ago

Research Intern: Interpretability & Reliability (Summer 2027)

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 11 hours agoStatus: Live

Job Summary

Join CTGT as a research intern to tackle a core problem in model interpretability and reliability. You will design, implement, and evaluate methods for feature extraction and runtime intervention across model families, collaborate with engineers to ship a Policy Engine capability, and present weekly progress while contributing to high-stakes AI governance research.
Location: San Francisco
Workplace: Onsite
Employment Type: Full time
Job Function: Research & Scientific (R&D)
Seniority: Intern level

Key Responsibilities

  • •Implement and stress-test methods for feature extraction and runtime intervention, across model families, ensuring repeatable results.
  • •Design evaluations that bound error rather than average it, including calibration under imbalanced data and reasoning-trace grading.
  • •Read relevant literature to decide what matters, reproduce it, and push past it.
  • •Collaborate with engineering to turn findings into Policy Engine capabilities for audited, high-stakes environments.
  • •Present progress weekly and defend your reasoning.

Pay and Benefits

Salary: USD 8,000 - 12,000 annually

Key Requirements

  • •Pursuing a degree (Bachelor's through PhD) in computer science, mathematics, the sciences, or a quantitatively rigorous field.
  • •Strong mathematical foundations: linear algebra, probability, optimization, information theory.
  • •Ability to read a paper, decide what matters, and implement it.
  • •Experience writing real code for computational systems; fluency with PyTorch and the modern ML stack (or demonstrable progress toward it).
  • •Interest in interpretability, model internals, and building reliable systems; self-directed with minimal scaffolding.
Experience:Artificial intelligenceMachine learningResearch
Skills:Problem-solvingCommunicationCritical thinkingCollaborationSelf-direction
Tech Stack:PythonRustNodeTypeScriptReactPostgreSQLVector databasesGraph databasesDockerKubernetesTerraformGPUCloud computing

Eligibility

Work Authorization:Sponsorship available.

Company Brief

CTGT
CTGT builds AI-driven software solutions that leverage machine learning to automate data analysis, generate insights, and streamline decision-making for enterprise clients across industries. Their platform focuses on scalable AI tooling, model deployment, and workflow integration to boost operational efficiency.
Industry: AI & Machine Learning
Website