Postdoctoral Research Fellow - VLM

Kappaalphapsi1911; Ann Arbor (MI); On-site; USD 65,000 - 85,000; Full time

Job summary

University of Michigan is seeking a Postdoctoral Research Fellow to lead a VLM-based adaptive perception project for robotic manipulation in manufacturing. You will work on-site in Ann Arbor with the CIMS Lab and sponsor collaboration with industry partners, focusing on perception, segmentation, and real-time integration on hardware.

The role requires a PhD in a related field, strong CV/ML background, and excellent communication.

Qualifications

• PhD in Mechanical Engineering or related field required.
• Strong background in computer vision and/or machine learning; hands-on deep learning experience.
• Excellent written and verbal communication skills.

Responsibilities

• Evaluate and benchmark vision-language models for adaptive robotic perception in industrial settings.
• Develop robust perception methods for object segmentation and pose estimation under real-world conditions.
• Integrate perception components into a real-time pipeline and validate on robotic hardware.
• Prepare technical reports, manuscripts, and presentations of research outcomes.
• Advise student research assistants supporting the project.

Skills

Robotic vision

Machine learning

Deep learning

Communication skills

Education

PhD in Mechanical Engineering or related field

PhD in Robotics or related field

Job description

# Postdoctoral Research Fellow - VLMUniversity of MichiganAnn Arbor, MIFull-TimeAug 15, 2026Education## Job Description## How to ApplyTo apply for this position, please email a cover letter, CV, and the names of two references to Professor Chenhui Shao at [email protected], with "[VLM Postdoc]" at the start of the subject line, and include in your cover letter how your expertise relates to this posting.Contact: Chenhui ShaoAssociate ProfessorDepartment of Mechanical EngineeringUniversity of Michigan## Who We AreAt 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.## Job SummaryRobotic 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.## Responsibilities\*- 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## Required Qualifications\*- 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- Strong demonstrated communication skills## Modes of WorkPositions 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.## Additional InformationAbout CIMS LabOur 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 MathWorks. Additional information about the group is available at: https://shaolab.engin.umich.edu/.## Background ScreeningThe 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 checks are performed in compliance with the Fair Credit Reporting Act.## Application DeadlineJob openings are posted for a minimum of seven calendar days. The review and selection process may begin 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.## U-M EEO StatementThe 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.