Job Description

‍

We’re looking for PhD candidates to intern on the Uber AI Platform team during winter 2026 (12 weeks). You will be embedded in our engineering team and work closely with other specialists, software developers, and product managers. As a PhD intern, you will contribute to research and development of AI agents for security and privacy. You’ll explore methods to build, evaluate, and scale agents that can reason about complex systems, detect vulnerabilities, propose and apply patches, and verify security outcomes.

‍

‍

‍

‍

About the Team

The AI platform (Michelangelo) team is dedicated to enhancing the development and production experiences for Deep Learning (DL) and Large Language Model (LLM) engineers and data scientists across all Uber products. We achieve this by building and operating a suite of tools that support every critical phase of the machine learning lifecycle, including feature engineering, distributed training, GPU resource management, model inference, ML-Ops, and monitoring. Our Canvas tool enables rapid and collaborative iteration during model development, with automatic scaling for robust deployment into production.

A key focus of this team is distributed training/inference for DL/LLM models within multi-GPU/TPU clusters. The team comprises talented individuals with diverse expertise, including modeling, framework development, GPU kernels, data loading, distributed algorithms, job controllers, and resource management.

‍

‍

‍

‍

‍

What You'll Do

• Design and build tools to empower production teams to innovate and productionize state-of-the-art DL/LLM models at Uber
• Develop and maintain scalable end-to-end training and inference systems
• Ensure tools developed are reliable, efficient, flexible to use for production
• Collaborate with cross-functional teams including machine learning engineers(MLE), backend engineers, data scientists/engineers to deliver robust ML solutions for Uber
• Utilize Generative AI Agents to enhance and expedite the model development process
• Document findings and contribute to technical reports, publications, or open-source tools

‍

‍

‍

‍

‍

‍

Basic Qualifications

• Current PhD student in Computer Science, Artificial Intelligence, or related fields
• Candidates must have at least one semester/quarter of their education left following the internship
• Strong understanding of the distributed DL training and inference system
• Proficiency in Python and experience with ML frameworks (e.g., PyTorch, TensorFlow, Ray, etc)
• Demonstrated ability to conduct independent research

‍

‍

‍

‍

‍

Preferred Qualifications

• Publications in top DL/LLM/AI conferences (e.g., NeurIPS, ICML, ICLR, etc)
• Experience on distributed training, model parallelism, GPU kernels (or alternative HW), and related SW like DDP, DeepSpeed, cuda, vLLM, etc.
• Familiarity with models like LLM, Recommendation system, NLP, CV, etc.
• Familiarity with resource management and Kuberate
• Strong problem-solving and communication skills

‍