Назад
Company hidden
2 дня назад

Senior/Lead Research Scientist, Model Evaluations (AI)

Формат работы
hybrid
Тип работы
fulltime
Грейд
senior/lead
Английский
b2
Страна
UK/Switzerland
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
Senior/Lead Research Scientist, Model Evaluations (AI): Building and scaling benchmark and evaluation suites for specialized professional LLMs with an accent on frontier-model research, multi-agent systems, and reliable evaluation. Focus on designing new benchmarks, translating legal and professional workflows into practical evaluations, and using research findings to guide model training, safety, and product development.

Location: Hybrid roles based in Zug, Switzerland, or London, United Kingdom

Company

hirify.global builds trusted content, software, and AI solutions for legal, tax, accounting, compliance, government, and media professionals. hirify.global Labs develops custom models for fiduciary-grade professional workflows.

What you will do

  • Build, operate, and scale the evaluation suite for Thomson models, identifying strengths, weaknesses, and coverage gaps.
  • Create benchmarks and evaluation assets based on product, external, and aspirational use cases for frontier models and agents.
  • Lead cross-functional work with scientists, engineers, product leaders, and subject-matter experts, and mentor junior scientists.
  • Inform model training objectives and technical direction through evaluation results, research, and recommendations on development trade-offs.
  • Conduct research across evaluation science, benchmarking, safety, and alignment; publish findings at leading AI, ML, and NLP conferences.
  • Integrate new research into model-development and product pipelines.

Requirements

  • Hands-on research experience designing, building, and releasing evaluations or benchmarks for frontier models or agents, including publications at top conferences such as NeurIPS, ICML, ICLR, or ACL.
  • Experience working with researchers and cross-functional stakeholders to translate ideas into practical evaluations.
  • Hands-on Python experience implementing benchmarks, agents, or other systems built around LLMs.
  • Familiarity with current LLM developments and an interest in following the evolving research frontier.
  • PhD in Computer Science or a related field, or equivalent practical experience, plus industry experience in post-training or evaluation.
  • Professional experience will be considered when determining the level between Senior and Lead.

Nice to have

  • Experience working with specialized domain experts in law, tax, or similar professions.
  • Familiarity with AI-assisted coding and using coding agents at scale.
  • Experience in experimental design and best practices for working with human data.

Culture & Benefits

  • Flexible hybrid work environment for office-based roles.
  • Work-from-anywhere arrangements are available for up to 8 weeks per year.
  • Flexible vacation, two company-wide mental health days, retirement savings, tuition reimbursement, incentive programs, and wellbeing resources.
  • Career development through continuous learning, skills-first programs, and Grow My Way programming.
  • Two paid volunteer days annually and opportunities for pro-bono consulting and ESG initiatives.
  • Values include customer focus, fast learning, critical thinking, inclusion, belonging, and work-life balance.

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 →