CareerPlanSign in

Research Intern - Fundamentals of AI: Security, Agents, Systems & Control

United States, Washington, Redmond💼 Internship🗓 2025-11-19 → 2026-09-27

Core

Develop methods to strengthen the robustness and trustworthiness of AI systems, design alignment strategies for agentic systems, and investigate architectures beyond transformers for controlled dynamical systems and multi-modal integration.

Role type

Research Intern (AI Safety & Systems)

Builds

Research prototypes and theoretical frameworks for AI alignment and robustness

Domain

Artificial Intelligence, Machine Learning, Control Systems

Deliverable

research

Required skills

AI system robustness, alignment strategies, post-training fine-tuning, agentic system orchestration, transformer architecture analysis, dynamical systems modeling, interpretable AI design, multi-modal integration

Preferred skills

Cross-functional collaboration, multi-disciplinary research

Technologies

Transformers, agentic systems, multi-modal models

Responsibilities

Design alignment strategies for post-training, investigate architectures for controlled dynamical systems, collaborate with doctoral candidates and researchers, present research findings

Seniority

Intern, research-focused

Sourced via microsoft · Listed on CareerPlan, which tracks 70,000+ jobs from 20+ sources.