Postdoctoral Research Fellow - VLM

Associate Professor

Department of Mechanical Engineering

University of Michigan

At Michigan Engineering, we develop the talent and technologies that move society forward and serve our state and national interests. Through discovery and innovation, we create the foundational knowledge and practical technologies to solve not only today's most pressing challenges, but also power industries and change lives. Our programs and community are designed to promote personal well-being and achievement - enabling everyone to unlock their potential and contribute with confidence.

Robotic manipulation in manufacturing environments, particularly pick-and-place operations, remains challenging when parts and environmental conditions vary. Conventional robotic systems rely on fixed object categories and require extensive manual reprogramming each time a new part or variant is introduced, which limits scalability and slows deployment in real-world production settings.

The Connected and Intelligent Manufacturing Systems (CIMS) Lab at the University of Michigan, in partnership with General Motors, is developing a Vision-Language Model (VLM)-based adaptive perception framework for robotic manipulation. By enabling robots to interpret semantic task instructions and generalize to new or variant parts with minimal reprogramming, this framework aims to substantially reduce the time and cost of deploying perception models for newly introduced components, while improving robustness to real-world variability such as lighting changes and occlusions.

This project spans model benchmarking, perception algorithm development, and integration and validation on physical robotic hardware. We are looking for a postdoctoral researcher to lead the technical execution of this project, with work performed on-site at the sponsor's facility.

• Evaluate and benchmark vision-language models for adaptive robotic perception in industrial applications
• Develop robust perception methods for object segmentation and pose estimation under real-world conditions such as occlusion, lighting variation, and diverse part geometries
• Integrate perception components into a real-time pipeline and validate on robotic manipulation hardware
• Prepare technical reports, manuscripts, and presentations documenting research outcomes
• Advise student research assistants supporting the project

• PhD in Mechanical Engineering, Robotics, Computer Science, Electrical Engineering, or a related field
• Strong background in computer vision and/or machine learning, with hands‑on experience in deep learning frameworks

Positions that are eligible for hybrid or mobile/remote work mode are at the discretion of the hiring department. Work agreements are reviewed annually at a minimum and are subject to change at any time, and for any reason, throughout the course of employment. Learn more about the work modes .

About CIMS Lab

Our research group is an interdisciplinary team dedicated to advancing the intelligence, quality, and efficiency of manufacturing. Our alumni have gone on to successful careers in academia, including at City University of Hong Kong, and have received full-time job offers from leading companies such as Meta, OpenAI, Google, KLA, Intel, Apple, 3M, C3 AI, Solventum, Milwaukee Tool, Lucid, Seagate, and Math Works.

Additional information about the group is available at: (Use the "Apply for this Job" box below). .

The University of Michigan conducts background checks on all job candidates upon acceptance of a contingent offer and may use a third party administrator to conduct background checks. Background checksare performed in compliance with the Fair Credit Reporting Act.

Job openings are posted for a minimum of seven calendar days.

The review and selection process maybegin as early as the eighth day after posting.

This opening may be removed from posting boards and filled any time after the minimum posting period has ended.

The University of Michigan is an Equal Opportunity Employer. We are committed to providing an environment of mutual respect where equal employment opportunities are available to all applicants, including protected veterans and individuals with disabilities.