6 дней назад
AI Evaluation Project Intern (Corporate Service System) - 2026 Start (BS/MS) (AI)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
AI Evaluation Project Intern (Corporate Service System) - 2026 Start (BS/MS) (AI): Designing and running evaluation benchmarks for AI agents used in workplace and procurement scenarios with an accent on user research, query and rubric design, model scoring, and automation. Focus on identifying capability gaps and failure modes, writing evaluation reports, and prototyping AI solutions for manual workflows and internal productivity tools.
Location: Dubai, United Arab Emirates; full-time onsite or at least 3 days per week onsite
Company
develops global content, social, creative, and AI-enabled products including TikTok, Lemon8, CapCut, and Pico.
What you will do
- Own a defined scope of AI evaluation benchmarks from research methodology through reporting and recommendations.
- Conduct user interviews, literature reviews, and usage data analysis to ground evaluations in real employee workflows.
- Design queries, prerequisites, scoring rubrics, and difficulty levels for workplace and procurement scenarios.
- Run and score AI agents and models, identify capability gaps and failure modes, and track results over time.
- Automate recurring evaluation workflows as models and internal systems evolve.
- Prototype AI solutions for manual workflows and contribute to new AI features in internal workplace and knowledge tools.
Requirements
- Currently pursuing an undergraduate degree in Computer Science, AI, Information Management, or a related technical discipline; strong hands-on AI experience from a non-CS background is also welcome.
- Available to start immediately, ideally within one week.
- Demonstrated logical thinking, self-direction, user focus, communication, and cross-team collaboration skills.
- Genuine interest in AI products and current developments in LLMs and AI agents.
- Must be able to work onsite in Dubai full time or onsite at least 3 days per week.
Nice to have
- Internship or project experience in AI products or AI evaluations.
- Experience designing or running LLM evaluations.
- Experience translating user problems into AI applications, especially in office automation or knowledge management.
Culture & Benefits
- Work with real employee workflows and users across 's global corporate services.
- Hands-on exposure to Claude, Doubao Seed 2.1, internal agent infrastructure, and agent-building tools.
- Opportunity to contribute to strategic AI projects and gain practical experience through short-term projects.
- Applications are reviewed on a rolling basis.
Hiring process
- Applications undergo resume screening.
- Candidates who pass screening complete a technical online assessment.
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 →