Research Intern - Self-Improving & Secure AI Agents - Microsoft Research

Posted 10 Hours Ago
Be an Early Applicant
Redmond, WA, USA
In-Office
82K-175K Annually
Internship
Software • Quantum Computing • Metaverse • Infrastructure as a Service (IaaS)
The Role
Conduct research on self-improving and secure AI agents. Develop methods for diagnosing capability gaps, synthesizing targeted training data, optimizing post-training loops, sandboxing agent execution, managing permissions, and defending against prompt injection and other agent attacks. Build prototypes, evaluate experiments, collaborate with researchers, present findings, and contribute to publications at top-tier venues.
Summary Generated by Built In
Overview

Research Internships at Microsoft provide a dynamic environment for research careers with a network of world-class research labs led by globally-recognized scientists and engineers, who pursue innovation in a range of scientific and technical disciplines to help solve complex challenges in diverse fields, including computing, healthcare, economics, and the environment.



We are seeking Research Interns to make long-horizon Artificial Intelligence (AI) agents both more capable and more secure. Agents increasingly act autonomously over long horizons and have access to tools, files, networks, and credentials. Two problems limit how far they can be trusted: they fail in ways that aggregate benchmark scores hide, and they can be manipulated by adversarial inputs. This Research Internship offers two research directions, with Research Interns focusing on one based on their expertise and interests:

  • Failure-driven self-improvement: improve long-horizon agents by diagnosing failure modes in their trajectories and synthesizing targeted post-training data that closes specific capability gaps.
  • Agent security: develop technologies that make existing agentic systems more secure, including sandboxing, agent permissions, and defenses against novel agent attacks.

Research Interns will contribute to one thrust, depending on their background. Expected outcomes include research prototypes, evaluation of pipelines, and publications at top-tier venues.


Responsibilities

Research Interns put inquiry and theory into practice. Alongside fellow doctoral candidates and some of the world’s best researchers, Research Interns learn, collaborate, and network for life. Research Interns not only advance their own careers, but they also contribute to exciting research and development strides. During the 12-week internship, Research Interns are paired with mentors and expected to collaborate with other Research Interns and researchers, present findings, and contribute to the vibrant life of 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

Project 1 — Self-Improving AI Agents

Develop and evaluate a research agent that uses post-training experiments to iteratively improve a target model through synthetic data.

  • Task decomposition and capability diagnosis. Develop methods for the agent to infer the capabilities required by a target task and use evaluation results to identify which capability gaps limit the model’s performance.
  • Capability-targeted data synthesis. Build methods that translate hypotheses about capability gaps into training data, with control over skill coverage, example difficulty, and data quality.
  • Closed loop optimization. Build a self-improvement loop that measures the effects of each round of synthetic data. Use these results to let the agent revise its capability hypotheses and adapt its data generation strategy across rounds.

Project 2 — Secure AI Agents

Develop and evaluate security mechanisms for existing AI agent systems.

  • Sandboxing. Isolate agent execution and control access to files, networks, and credentials.
  • Agent permissions. Develop least-privilege authorization, task-scoped permissions, and approval mechanisms for sensitive actions.
  • Agent attacks and defenses. Study prompt injection, malicious tool outputs, memory poisoning, and cross-agent attacks in controlled environments. Prototype defenses in an existing agent framework and evaluate their security effectiveness, impact on task performance, and usability.

Across both projects, Research Interns will collaborate with researchers to communicate findings to technical audiences and pursue publication at top-tier venues


Qualifications
Required Qualifications
  • Currently enrolled in a Doctorate Degree program in computer science, machine learning, artificial intelligence, cybersecurity, or a related field.


Other Requirements

  • Research Interns are expected to be physically located in their manager’s Microsoft worksite location for the duration of their internship.
  • In addition to the qualifications below, you’ll need to submit a minimum of two reference letters for this position as well as a cover letter and any relevant work or research samples. After you submit your application, a request for letters may be sent to your list of references on your behalf. Note that reference letters cannot be requested until after you have submitted your application, and furthermore, that they might not be automatically requested for all candidates. You may wish to alert your letter writers in advance, so they will be ready to submit your letter. 

Preferred Qualifications
  • Demonstrated Python programming skills and hands-on experience with PyTorch or a similar machine learning (ML) framework.
  • Publications at top-tier ML conferences such as NeurIPS, ICML, ICLR, ACL, or related venues.
  • Highly self-driven, with the ability to work independently and collaborate effectively in a fast-moving research environment.
  • Background in one or more systems of security, sandboxing, access control, or Large Language Model (LLM)-based agents.
  • Demonstrated mathematical foundations and modeling ability.
  • Demonstrated hands-on software engineering skills, demonstrated by independently building tools, small systems, or software projects from scratch. Open-source contributions are a plus.
  • High-level awards or equivalent achievements in competitive programming, mathematics, or algorithmic competitions such as ICPC.
  • Interest in security research and ability to design experiments, analyze results, and communicate findings.


The base pay range for this internship is USD $6,810 - $13,480 per month. There is a different range applicable to specific work locations, within the San Francisco Bay area and New York City metropolitan area, and the base pay range for this role in those locations is USD $8,920 - $14,610 per month.


Certain roles may be eligible for benefits and other compensation. Find additional benefits and pay information here: https://careers.microsoft.com/us/en/us-intern-pay


Microsoft accepts applications and processes offers for these roles on an ongoing basis throughout the academic calendar (September - April).


This position will be open for a minimum of 5 days, with applications accepted on an ongoing basis until the position is filled.



Microsoft is an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to age, ancestry, citizenship, color, family or medical care leave, gender identity or expression, genetic information, immigration status, marital status, medical condition, national origin, physical or mental disability, political affiliation, protected veteran or military status, race, ethnicity, religion, sex (including pregnancy), sexual orientation, or any other characteristic protected by applicable local laws, regulations and ordinances. If you need assistance with religious accommodations and/or a reasonable accommodation due to a disability during the application process, read more about requesting accommodations.

Skills Required

  • Currently enrolled in a Doctorate Degree program in computer science, machine learning, artificial intelligence, cybersecurity, or a related field.
  • Physically located at the manager's Microsoft worksite for the duration of the internship.
  • Submit at least two reference letters.
  • Submit a cover letter and relevant work or research samples.
  • Demonstrated Python programming skills and hands-on experience with PyTorch or a similar machine learning framework.
  • Publications at top-tier machine learning conferences such as NeurIPS, ICML, ICLR, or ACL.
  • Background in security systems, sandboxing, access control, or large language model-based agents.
  • Demonstrated mathematical foundations and modeling ability.
  • Hands-on software engineering experience building tools, small systems, or software projects from scratch.
  • High-level awards or equivalent achievements in competitive programming, mathematics, or algorithmic competitions.
  • Interest in security research and ability to design experiments, analyze results, and communicate findings.

Microsoft Compensation & Benefits Highlights

The following summarizes recurring compensation and benefits themes identified from responses generated by popular LLMs to common candidate questions about Microsoft and has not been reviewed or approved by Microsoft.

  • Healthcare Strength — Medical, dental, and vision coverage is described as comprehensive, with U.S. plans covering preventive care at 100% and limiting annual out-of-pocket costs. Mental-health counseling, employee assistance, and wellbeing resources are also emphasized.
  • Parental & Family Support — Parental leave, family-caregiver leave, childcare assistance, and family concierge services are highlighted as core elements. These supports are presented alongside parenting and family-planning resources.
  • Leave & Time Off Breadth — Vacation, holidays, and flexible work schedules are emphasized, with generous time-away policies noted. Leave options extend beyond standard vacation to include caregiver and parental programs.

Microsoft Insights

Am I A Good Fit?
beta
Get Personalized Job Insights.
Our AI-powered fit analysis compares your resume with a job listing so you know if your skills & experience align.

The Company
HQ: Redmond, WA
206,870 Employees
Year Founded: 1975

What We Do

At Microsoft, our mission is to empower every person and every organization on the planet to achieve more. Our mission is grounded in both the world in which we live and the future we strive to create. Today, we live in a mobile-first, cloud-first world, and the transformation we are driving across our businesses is designed to enable Microsoft and our customers to thrive in this world.

Similar Jobs

SailPoint Logo SailPoint

Staff Software Engineer

Artificial Intelligence • Cloud • Sales • Security • Software • Cybersecurity • Data Privacy
Remote or Hybrid
United States
2461 Employees
156K-263K Annually

Circle Logo Circle

VP, Agentic Partnerships & GTM

Blockchain • Fintech • Payments • Financial Services • Cryptocurrency • Web3
In-Office or Remote
25 Locations
1050 Employees
288K-330K Annually

Expedia Group Logo Expedia Group

Senior Business Performance Insights Manager

AdTech • eCommerce • Information Technology • Software • Travel • Generative AI
Hybrid
Seattle, WA, USA
16000 Employees
155K-248K Annually

Expedia Group Logo Expedia Group

Scientist

AdTech • eCommerce • Information Technology • Software • Travel • Generative AI
Hybrid
Seattle, WA, USA
16000 Employees
231K-399K Annually

Similar Companies Hiring

Ford Energy Thumbnail
Automotive • Software • Energy • Utilities • Manufacturing • Renewable Energy
US
Revel Thumbnail
Aerospace • Hardware • Robotics • Software
Marina Del Rey, California
70 Employees
Blee Thumbnail
Artificial Intelligence • Marketing Tech • Software
New York, New York
33 Employees

Sign up now Access later

Create Free Account

Please log in or sign up to report this job.

Create Free Account