Назад
Company hidden
10 дней назад

Interpretability Researcher (Mechanistic Interpretability)

200 000 - 600 000$
Формат работы
onsite
Тип работы
fulltime
Грейд
senior
Английский
b2
Страна
US
Вакансия из списка Hirify.GlobalВакансия из Hirify Global, списка международных tech-компаний
Для мэтча и отклика нужен Plus

Мэтч & Сопровод

Для мэтча с этой вакансией нужен Plus

Описание вакансии

Текст:
/
TL;DR
Interpretability Researcher (Mechanistic Interpretability) (AI): Investigating model internals, neural circuits, and learned representations while building AI agents and research infrastructure for automated mechanistic interpretability experiments with an accent on activation analysis, sparse autoencoders, and causal interventions. Focus on developing evaluation frameworks, experimental pipelines, and feedback mechanisms that improve AI-assisted research.

Location: On-site in New York City or San Francisco

Salary: $200,000–$600,000

Company

hirify.global is working with a well-funded Series A frontier AI research company that has raised $60M and develops research infrastructure for autonomous AI agents in collaboration with frontier AI labs.

What you will do

  • Investigate model internals, neural circuits, and learned representations.
  • Develop AI agents that automate mechanistic interpretability experiments.
  • Build research tools, evaluation frameworks, and experimental pipelines.
  • Explore training tasks and feedback mechanisms that improve AI-assisted research.
  • Collaborate across interpretability, reinforcement learning, and AI alignment research.

Requirements

  • L5–L7+ level research hire.
  • Research experience in mechanistic interpretability, model internals, or representation learning.
  • Hands-on experience with activation analysis, sparse autoencoders, circuit discovery, or causal interventions.
  • Strong Python and PyTorch skills with practical research engineering capabilities.
  • Original research, publications, or meaningful open-source contributions.

Nice to have

  • Experience with AI agents, automated experimentation, or research tooling.

Culture & Benefits

  • Work directly with frontier AI labs.
  • Join a heavily backed AI research team focused on understanding how neural networks work internally.
  • Research locations include New York City and San Francisco.

Hiring process

  • Apply directly or message the recruiter for a confidential discussion.

Будьте осторожны

Если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого. Это мошенники. Обязательно жмите «Пожаловаться» или пишите в поддержку. Подробнее в гайде →