CrawlJobs Logo

Research Intern - AI Safety and Security

United States, Redmond 6710.00 - 13270.00 USD / Month · Job Posted March 13, 2026
Apply Position
Job Link Share

Job Description

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. Protecting large language models (LLMs) from malicious inputs is critical. LLMs can also be used to protect users from malicious attacks. The Deep Learning Team in Microsoft Research – Redmond is seeking Research Interns interested in the areas of LLM safety or using LLMs for computer security.

Job Responsibility

  • Research Interns put inquiry and theory into practice
  • Learn, collaborate, and network for life
  • Contribute to exciting research and development strides
  • Collaborate with other Research Interns and researchers
  • Present findings
  • Contribute to the vibrant life of the community

Requirements

  • Currently enrolled in a PhD program in Computer Science or a related STEM field
  • Demonstrated ability to develop original research agendas
  • Knowledge of LLMs
  • Proficient coding skills in Python and deep learning platforms
  • Ability to collaborate effectively with other researchers and product development teams
  • Demonstrated interpersonal skills, cross-group, and cross-culture collaboration

Looking for more opportunities?

Search for other job offers that match your skills and interests.

Similar Jobs for

Research Intern - AI Safety and Security

8 matching positions

Head of Policy & Security Research Lab

We are seeking a highly experienced, strategic and mission-driven leader to driv...
Location
Location
United States , San Francisco, CA; New York, NY; Washington, DC
Salary
Salary:
198000.00 - 247000.00 USD / Year
scale.com Logo
Scale
Expiration Date
Until further notice
Flip Icon
Requirements
Requirements
  • 6+ years of relevant academic or work experience
  • A track record of impactful research and/or policy contributions
  • Experience leading teams in relevant areas including AI Safety Policy, Thought Leadership and Research publications
  • Strong written and verbal communication skills for cross-functional collaboration
  • Experience building and mentoring teams of research scientists and engineers
  • A strong technical and policy background with a deep understanding of the AI safety space
  • Extensive knowledge of frontier risk evaluations, AI control, and preparedness research
  • Established connections with government partners, particularly AI safety institutes.
Job Responsibility
Job Responsibility
  • Own day-to-day responsibilities for the strategy, direction and execution of Scale’s Policy Research Lab
  • Collaborate with a team of internal researchers, leading research labs across governments, industry, and academia
  • Working alongside a team of internal researchers drive initiatives related to frameworks and benchmarks for frontier AI models
  • Remain deeply engaged with the policy and research communities to understand and set trends
  • Manage and coordinate the lab's projects, partnerships and strategy, including direct work with global AI safety institutes
  • Finalize, coordinate, and execute the lab's recruiting plan and research agenda.
What we offer
What we offer
  • comprehensive health, dental and vision coverage
  • retirement benefits
  • a learning and development stipend
  • generous PTO
  • commuter stipend
  • Fulltime
Read More
Arrow Right

Member of Technical Staff, Microsoft Robotics (Robot Security & Safety)

Microsoft's Discovery and Quantum (MDQ) division develops and delivers advanced ...
Location
Location
United States , Redmond
Salary
Salary:
119800.00 - 234700.00 USD / Year
https://www.microsoft.com/ Logo
Microsoft Corporation
Expiration Date
Until further notice
Flip Icon
Requirements
Requirements
  • Bachelor's Degree in Computer Science or related technical field AND 4+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or Python OR equivalent experience.
  • Ability to meet Microsoft, customer and/or government security screening requirements are required for this role. These requirements include but are not limited to the following specialized security screenings: Microsoft Cloud Background Check: This position will be required to pass the Microsoft Cloud Background Check upon hire/transfer and every two years thereafter.
Job Responsibility
Job Responsibility
  • Design and implement end-to-end security and safety architectures for robotic systems, spanning the full hardware-software robot stack, including device-level security (secure boot, firmware integrity, encrypted communications), platform-level security (identity, access control, certificate management), and cloud-to-edge security for robot fleet management.
  • Develop and maintain safety analyses and threat models (FMEA, FTA, HAZOP, STPA) specific to robotic systems operating in human-populated environments, identifying risks from cyber-attack vectors, AI behavior failures, hardware faults, and environmental uncertainties.
  • Define and enforce safety envelopes and runtime safety monitors for autonomous robot behaviors, including collision avoidance, force limiting, workspace boundaries, and graceful degradation under sensor or actuator failure conditions.
  • Analyze key security metrics, KPIs, and telemetry data to identify trends in security posture and safety incidents, implementing mitigation strategies and driving continuous improvement of the platform's security and safety posture.
  • Design and scale solutions to address identified security control issues (network, identity, applications) and current threats specific to robotics deployments, anticipating and articulating risks to leadership.
  • Develop and implement incident response processes for robotics-specific security and safety events, including physical safety incidents, AI behavior anomalies, fleet compromise scenarios, and supply chain integrity concerns.
  • Collaborate with robotics engineers, AI researchers, and platform engineers to embed security and safety requirements into the software development lifecycle, including secure coding standards, security testing in CI/CD pipelines, and safety validation in simulation.
  • Contribute to the development and implementation of security policies and standards for robotic systems, aligning with industry frameworks (NIST, MITRE ATT&CK for ICS, IEC 61508, ISO 13482, ISO 10218, RIA standards) and Microsoft's security requirements.
  • Engage with regulatory bodies, industry standards organizations, and Microsoft internal AI safety and security communities (e.g., Microsoft's Office of Responsible AI), to stay current on evolving safety and security requirements for autonomous and AI-enabled physical systems.
  • Leverage automation and AI to improve effectiveness of security operations, including automated vulnerability scanning, anomaly detection in robot telemetry, and AI-assisted threat hunting across the robotics fleet.
  • Fulltime
Read More
Arrow Right

Senior Applied Scientist, AI Security

Our mission is to make Uber the industry model for a secure and trustworthy AI e...
Location
Location
United States , Sunnyvale
Salary
Salary:
190000.00 - 211000.00 USD / Year
uber.com Logo
Uber
Expiration Date
Until further notice
Flip Icon
Requirements
Requirements
  • Ph.D., MS or Bachelors degree in Statistics, Economics, Operations Research, Computer Science, Engineering, or other quantitative field
  • If Ph.D or M.S. degree, a minimum of 2+ years of industry experience as an Applied Scientist or equivalent
  • Knowledge of underlying mathematical foundations of machine learning, statistics, optimization, economics, and analytics
  • Hands-on experience building and deploying ML models
  • Knowledge of experimental design and analysis
  • Experience with exploratory data analysis, statistical analysis and testing, and model development
  • Ability to use a language like Python or R to work efficiently at scale with large data sets
  • Proficiency in technologies in one or more of the following: SQL, Spark, Hadoop
Job Responsibility
Job Responsibility
  • Develop and evaluate large-scale machine learning model systems in production with a focus on adversarial robustness, input validation, and output sanitization
  • Propose, design, and analyze large-scale online experiments to test safety guardrails and detect ecosystem vulnerabilities
  • Define and implement metrics to measure security posture, attack surface reduction, and product performance
  • Present findings on AI risks, red-teaming results, and mitigations to business and executive audiences
  • Collaborate with engineers and product managers to implement secure-by-design ideas and plan future roadmaps
  • Optimize and secure retrieval-augmented generation (RAG) systems against prompt injection, indirect injection, and data exfiltration
  • Fine-tune large language models (LLMs) to improve safety alignment, resistance to jailbreaking, and operational efficiency
  • Implement secure agentic workflows to streamline processes, ensuring safe tool-use and authorization for both internal employee agents and external user agents
What we offer
What we offer
  • Eligible to participate in Uber's bonus program
  • May be offered an equity award & other types of comp
  • All full-time employees are eligible to participate in a 401(k) plan
  • Eligible for various benefits (see link)
  • Fulltime
Read More
Arrow Right
New

Senior Applied Scientist

Frontier Tuning is Microsoft’s AI customization platform that enables enterprise...
Location
Location
United Kingdom , Multiple Locations
Salary
Salary:
74700.00 - 122600.00 GBP / Year
https://www.microsoft.com/ Logo
Microsoft Corporation
Expiration Date
Until further notice
Flip Icon
Requirements
Requirements
  • Bachelor's Degree in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND advanced related experience (e.g., statistics predictive analytics, research)
  • OR Master's Degree in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND solid related experience (e.g., statistics, predictive analytics, research)
  • OR Doctorate in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND some related experience (e.g., statistics, predictive analytics, research)
  • OR equivalent experience
  • Experience contributing to research, open‑source systems, or production deployments involving model training or adaptation
  • Ability to meet Microsoft, customer and/or government security screening requirements are required for this role
  • Microsoft Cloud Background Check: This position will be required to pass the Microsoft Cloud background check upon hire/transfer and every two years thereafter
  • Master's Degree in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND extensive related experience (e.g., statistics, predictive analytics, research)
  • OR Doctorate in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND advanced related experience (e.g., statistics, predictive analytics, research)
  • OR equivalent experience
Job Responsibility
Job Responsibility
  • Design and develop methods to adapt foundation models (e.g., language, diffusion, or multimodal models) for enterprise‑specific tasks such as document understanding, workflow automation, or content generation
  • Contribute to one or more aspects of the post-training stack, including: Reinforcement learning or fine-tuning methods
  • Architectural or parameter‑efficient adaptation techniques
  • Inference‑time steering or controllability approaches
  • Tooling for evaluation, debugging, or model development
  • Privacy- or security‑preserving training techniques (e.g., differential privacy)
  • Harnesses
  • Implement and evaluate adaptation approaches under real‑world enterprise deployment constraints such as latency, safety, privacy, policy compliance, and compute efficiency
  • Partner with research and engineering teams to translate product or customer requirements into scalable model adaptation solutions
  • Explore post‑training techniques that improve domain specialization, tool use, planning, or agentic behaviors in enterprise environments
  • Fulltime
Read More
Arrow Right

Principal Software Engineer, CoreAI

The CoreAI AI Platform team is seeking a Principal Software Engineer in Redmond,...
Location
Location
United States , Redmond
Salary
Salary:
142800.00 - 304200.00 USD / Year
https://www.microsoft.com/ Logo
Microsoft Corporation
Expiration Date
Until further notice
Flip Icon
Requirements
Requirements
  • Bachelor's Degree in Computer Science or related technical field and 6+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, Python or equivalent experience.
Job Responsibility
Job Responsibility
  • Lead the architecture and implementation of large-scale platform services that support complex engineering and AI workflows in distributed cloud environments
  • Build internal tooling and automation that improve productivity for engineers and researchers across experimentation, deployment, and operational workflows
  • Design platform capabilities that make data easier to discover, access, and use in secure, governed, and auditable ways
  • Drive operational excellence through improvements in reliability, observability, deployment safety, and incident readiness
  • Partner across teams to resolve cross-cutting technical problems and align architecture, engineering standards, and long-term investments
  • Mentor engineers, contribute to technical reviews, and help raise the engineering bar across the organization
  • Fulltime
Read More
Arrow Right

Ai Policy Manager

Meta is looking for an AI Policy Manager to join our AI Policy team. In this rol...
Location
Location
United States , Washington
Salary
Salary:
122000.00 - 180000.00 USD / Year
meta.com Logo
Meta
Expiration Date
Until further notice
Flip Icon
Requirements
Requirements
  • 5+ years of experience in public policy
  • Proven understanding of the AI policy landscape, including key debates around safety, governance, ethics, and accountability
  • Experience in analyzing AI technology for policy and governance, including the ability to: Translate technical system behavior into policy-relevant concepts (e.g., capability, limitations, uncertainty, and foreseeable misuse)
  • Assess risks and impacts such as safety, privacy, security, bias/fairness, explainability, transparency, and content integrity
  • Evaluate governance mechanisms (e.g., risk assessments, model documentation, audits, red-teaming, incident response, and post-deployment monitoring) and how they map to emerging regulatory and standards frameworks
  • Engage effectively with technical and cross-functional partners to inform policy positions, compliance strategies, and responsible AI decision-making
  • Experience in building and managing relationships with external stakeholders, such as academics, researchers, and civil society organizations
  • Proven track record of communication and presentation skills, with demonstrated experience successfully conveying complex policy issues to a wide range of audiences
Job Responsibility
Job Responsibility
  • Develop and maintain Meta’s advocacy positions on a wide range of AI policy issues, ensuring they are aligned with our product roadmap and broader policy objectives
  • Collaborate with cross-functional partners to ensure a coordinated and effective approach to AI policy
  • Support the team’s engagement with a global network of third-parties, including academic institutions, research centers, and civil society organizations
  • Track and analyze emerging AI policy issues and trends, providing insights and recommendations to internal teams
  • Prepare briefing materials and other advocacy materials for internal and external use
  • Represent Meta in external forums, including academic conferences and policy workshops, as needed
What we offer
What we offer
  • bonus
  • equity
  • benefits
  • Fulltime
Read More
Arrow Right

Staff Research Scientist - VLM / VLA

At General Motors, our product teams are redefining mobility. Through a human-ce...
Location
Location
United States , Mountain View
Salary
Salary:
218800.00 - 335300.00 USD / Year
gm.com Logo
General Motors
Expiration Date
Until further notice
Flip Icon
Requirements
Requirements
  • Ph.D. in Machine Learning, Robotics, Computer Science, Electrical Engineering, or a related technical field
  • 5+ years of experience in AI/ML research and applied development
  • Deep expertise in modern ML architectures (transformers, generative AI, multimodal systems)
  • Strong programming skills in Python
  • Excellent communication, collaboration, and mentoring abilities, comfortable influencing technical strategy and guiding ML excellence across the organization
Job Responsibility
Job Responsibility
  • Research, design, and prototype advanced Vision-Language Models and Vision-Language-Action foundational models tailored for real-time semantic understanding and behavioral prediction in autonomous driving
  • Drive the technical strategy for onboard model optimization, leading initiatives in model quantization, pruning, knowledge distillation, and compilation to ensure high-parameter models execute with ultra-low latency on vehicle edge hardware
  • Advance multimodal alignment techniques, ensuring seamless integration of camera, radar, LiDAR, and textual/logical prompts into unified foundational architectures
  • Influence technical roadmaps and shape strategic machine learning priorities that align with safety requirements, core product milestones, and next-generation vehicle launches
  • Provide technical mentorship and long-term vision to a multidisciplinary group of machine learning engineers, software developers, and hardware specialists
  • Foster internal innovation by collaborating closely with perception, planning, and infrastructure teams to integrate foundational models into the core autonomous software stack
  • Represent the company externally to the global scientific community by publishing original research, securing patents, and presenting at top-tier artificial intelligence and robotics conferences
What we offer
What we offer
  • Medical
  • dental
  • vision
  • Health Savings Account
  • Flexible Spending Accounts
  • retirement savings plan
  • sickness and accident benefits
  • life insurance
  • paid vacation & holidays
  • tuition assistance programs
  • Fulltime
Read More
Arrow Right

Principal Technical Program Manager (Quantum Hardware and Firmware Systems)

Microsoft Quantum team is dedicated to developing the first scalable, fault-tole...
Location
Location
United States , Redmond
Salary
Salary:
139900.00 - 274800.00 USD / Year
https://www.microsoft.com/ Logo
Microsoft Corporation
Expiration Date
Until further notice
Flip Icon
Requirements
Requirements
  • Bachelor's Degree AND 6+ years experience in quantum information, physics, materials science, electrical engineering, hardware systems, engineering, or related technical fields OR equivalent experience
  • 3+ years of experience managing cross-functional and/or cross-team projects.
  • Ability to meet Microsoft, customer and/or government security screening requirements are required for this role. These requirements include, but are not limited to the following specialized security screenings:Microsoft Cloud Background Check: This position will be required to pass the Microsoft Cloud Background Check upon hire/transfer and every two years thereafter.
  • Citizenship & Citizenship Verification: This role will require access to information that is controlled for export under export control regulations, potentially under the U.S. International Traffic in Arms Regulations or Export Administration Regulations, the EU Dual Use Regulation, and/or other export control regulations. As a condition of employment, the successful candidate will be required to provide proof of citizenship, U.S. permanent residency, or other protected status (e.g., under 8 U.S.C. § 1324b(a)(3)) for assessment of eligibility to access the export-controlled information. To meet this legal requirement, and as a condition of employment, the successful candidate's citizenship will be verified with a valid passport. Lawful permanent residents, refugees, and asylees may verify status using other documents, where applicable.
  • Ability to leverage AI tools to drive innovation and efficiency (e.g., performance modeling and analysis, research gathering, day to day task automation).
  • Apply AI to accelerate engineering and lab workflows. Design and build AI agents/copilots that assist with experiment setup, log triage, measurement report generation, protocol templating, and knowledge retrieval (e.g., instrument manuals, design docs).
  • Evaluate agentic solutions with measurable metrics and humanintheloop safeguards following Microsoft Responsible AI requirements for generative AI.
  • 10+ years of experience owning and managing multi-year, highly complex hardware and firmware product portfolios involving deep-tech or first-of-a-kind technologies, including board bring-up, System-on-Chip (SoC) bring-up, BIOS and driver development, Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs), quantum systems, advanced chip packaging, cryoelectronics, or other high-reliability hardware.
  • Experience managing firmware and hardware product development across the full lifecycle, including R&D, system integration, hardware-software integration, new-technology introduction, and technology transfer from R&D into scaled engineering and manufacturing, including hardware quality systems and development or auditing of test and validation protocols.
  • Experience with hands-on firmware, low-level systems, or advanced hardware R&D, including BIOS, drivers, embedded systems, quantum device development, quantum error correction, measurement/control systems, or similar advanced hardware domains.
Job Responsibility
Job Responsibility
  • Drive Program Execution: Lead comprehensive program management for pivotal quantum hardware initiatives. Oversee all phases, including concept development, engineering design, prototyping, validation, operational scaling, and ongoing delivery. Collaborate closely with system architects, research scientists, and hardware engineers to ensure successful outcomes for each project
  • Strategic Planning & Roadmapping: Work with program management leadership, engineering teams, and executive stakeholders to develop and maintain a clear roadmap for hardware platform advancement. Align technical milestones, allocate resources, manage schedules, and address risks to support Microsoft Quantum’s overarching long-term goals
  • Cross-Disciplinary Coordination: Facilitate collaboration and alignment among teams specializing in quantum device physics, cryoelectronics, materials science, hardware control, manufacturing, supply chain, integration, and cloud hardware operations. Ensure that integrated efforts result in reliable and scalable hardware solutions
  • Supplier & Partner Engagement: Manage relationships with external foundries, research laboratories, equipment vendors, and strategic partners. Foster cross-company collaboration, establish clear requirements, and ensure compliance with Microsoft’s standards for quality, safety, and data security
  • Risk Management: Identify, monitor, and mitigate technical, scheduling, and operational risks throughout program execution. Apply continuous improvement strategies and adjust programs in response to lessons learned and evolving technology trends
  • Agile Delivery: Oversee Agile program processes and ceremonies, promote transparency by conducting regular reviews and updates, and proactively remove obstacles to ensure timely achievement of critical deliverables
  • Customer Focus: Incorporate feedback from internal and pilot customers—including researchers, manufacturing partners, and Azure Quantum platform teams—to guide improvements in hardware and processes
  • Executive Communication: Develop concise, data-driven reports and executive updates that communicate program status, milestones, risks, dependencies, and impact, upholding Microsoft’s high standards for stakeholder engagement and reporting
  • Embody our culture and values
  • Fulltime
Read More
Arrow Right