Skip to main content

AI Safety Research Intern

MicrosoftRedmond, WAPosted 16 minutes ago

Pay
$82k – $162k
per year
Type
Internship
Full time
Where
Redmond, WA
Who
PhD
Students
Apply by
Dec 19, 2026
Date from the posting

Overview

Research Internships at Microsoft offer a dynamic setting for research careers, with a network of world-class research labs led by globally recognized scientists and engineers. These teams pursue innovation across many scientific and technical disciplines, including computing, healthcare, economics, and the environment.

Our group studies alignment and safety in frontier Artificial Intelligence (AI) systems, linking evaluation, automated red teaming, and post-training. We develop new evaluations to surface emerging risks such as deception, sandbagging, misalignment, and unsafe autonomous behavior. We also build automated red-teaming systems that stress-test models and agents in realistic environments. These signals then inform post-training methods that improve safety without sacrificing capabilities. Interns work on open research problems spanning frontier evaluations, red teaming, alignment science, and safety post-training.

Responsibilities

Research Interns bring inquiry and theory into practice. They work alongside fellow doctoral candidates and some of the world's best researchers, learning, collaborating, and building a network for life. Interns advance their own careers while contributing to research and development progress.

During the 12-week internship, Research Interns are paired with mentors and are expected to collaborate with other interns and researchers, present findings, and take part in the community. Research internships are available in all areas of research and are offered year-round, though they typically begin in the summer.

Additional Responsibilities

  • Own a scoped research project in AI alignment, frontier evaluations, red teaming, or safety post-training.
  • Design and run experiments on frontier models and agentic systems.
  • Build new evaluations and automated red-teaming approaches for identifying emerging safety risks.
  • Develop or evaluate post-training techniques aimed at improving model behavior.
  • Work with researchers and engineers to turn experimental findings into scientific insights, publications, and improvements to deployed AI systems.

Other Requirements

Research Interns must be physically located at their manager's Microsoft worksite location for the duration of the internship. Applicants must submit a minimum of two reference letters, a cover letter, and any relevant work or research samples. Reference letters may be requested after the application is submitted, and they might not be requested for all candidates.

Preferred Qualifications

  • Demonstrated research background in machine learning and foundation models.
  • Experience conducting empirical research with large language models.
  • Familiarity with AI alignment, frontier evaluations, red teaming, or post-training.
  • Demonstrated programming, experimentation, and quantitative analysis skills.
  • Research experience studying alignment and safety of frontier AI systems.
  • Experience developing novel evaluations or automated red-teaming methods for advanced models and agents.
  • Experience with post-training methods, including reinforcement learning, supervised fine-tuning, or preference-based methods.
  • Interest in empirically studying emerging behaviors such as deception, sandbagging, reward hacking, and agentic misalignment.

Skills mentioned

  • Machine Learning
  • Large Language Models
  • Reinforcement Learning
  • Red Teaming
  • AI Alignment

Related news: Nadella says Microsoft buyouts were about AI-driven job changes

More jobs at MicrosoftSee all 35

Research Intern

Microsoft · Redmond, WA

  • Internship
  • Summer 2027
  • Hybrid

$82k – $175k /yr

New, posted 1 hour ago

Research Intern

Microsoft · Redmond, WA

  • Internship
  • Hybrid

$82k – $162k /yr

1 day ago

Browse more jobs

$82k – $162k /yr

Microsoft

Apply (opens in a new tab)