Назад
Company hidden
обновлено 2 дня назад

PhD Position AI Alignment (AI Engineering)

3 059 - 3 881
Формат работы
hybrid
Тип работы
fulltime
Грейд
trainee
Английский
b2
Страна
Netherlands
Релокация
Netherlands
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

PhD Position AI Alignment (AI Engineering): Developing and operationalizing human and legal values into alignment pipelines for AI systems and foundation models with an accent on quantifiable engineering metrics and automated validation. Focus on designing red-teaming frameworks and evaluating open-weights models for high-risk law enforcement deployments.

Location: Hybrid in Delft, Netherlands. Must be based in or be able to relocate to the Netherlands; includes a requirement to spend 20% of time at the Netherlands Police strategy and innovation division.

Salary: €3,059 – €3,881 per month

Company

hirify.global is a leading international university specializing in engineering and research to create concrete solutions for global societal challenges.

What you will do

  • Formalize value taxonomies and alignment metrics for open-weights foundation models in sensitive public-facing domains.
  • Define mathematical and procedural constructs for trustworthiness and fairness within complex law enforcement workflows.
  • Design and implement scalable methodologies to systematically stress-test, audit, and benchmark AI models.
  • Explore downstream alignment techniques such as DPO, RLHF, or Constitutional AI to enforce organizational values.
  • Collaborate with the Netherlands Police and the Delft Digital Ethics Centre to bridge academic research and practical implementation.

Requirements

  • MSc in Computer Science, Data Science, or Ethics of AI with practical ML/AI project and thesis experience.
  • Strong command of the Dutch language is a prerequisite for stakeholder interaction and data analysis.
  • Must pass a mandatory security screening executed by the Dutch government (screening process can take 2-6 months).
  • Good command of written and spoken English for an international academic environment.
  • Strong motivation to conduct research applied to real-world security domains.

Nice to have

  • Keen interest in human-AI interaction and explainable AI (XAI).
  • Experience collaborating with experts across different scientific and non-scientific disciplines.

Culture & Benefits

  • 5-year employment contract with incremental salary increases based on the Collective Labour Agreement for Dutch Universities.
  • Additional compensation including 8% holiday allowance and an 8.3% end-of-year bonus.
  • Comprehensive doctoral training and mentorship via the hirify.global Graduate School.
  • Relocation support through the Coming to Delft Service and a Dual Career Programme for partners.
  • Flexible work schedules and a customizable compensation package.

Hiring process

  • Application submission including CV and motivational letter.
  • Knowledge security risk assessment during the final stages of selection.
  • Prerequisite security screening (BO screening) by the Dutch government before the contract comes into effect.

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 →