VLM-based Scene Understanding Research Intern

Bosch • Sunnyvale, CA

392d • $85,280 - $141,440

About The Position

The Bosch Research and Technology Center North America is seeking a Ph.D. student or highly qualified M.S. student for an internship focused on building an advanced cloud-based system for sparse semantic scene understanding using Vision Language Models (VLMs). The role involves architecting a cloud-retrieval pipeline, implementing systems for localization and mapping, and summarizing research findings for publication. This position offers an opportunity to work on cutting-edge AI technologies in a collaborative environment.

Requirements

• Ph.D. student or highly qualified M.S. student in Computer Science, Machine Learning, Robotics, or related fields (Must be a current student or recent graduate - less than 1 year)
• Hands-on experience in setting up and running computer vision technologies, such as YOLO, SAM, etc.
• Hands-on experience in setting up and running VLMs or LLMs
• Experience with localization and mapping algorithms, such as SLAM or place recognition
• Knowledgeable on the state-of-the-art in VLM/LLM ideas and software
• Solid C++ and Python programming skills
• Hands-on experience working with robotic middlewares such as ROS2 or FogROS2.

Nice To Haves

• Publication record in top venues (ICRA, IROS, RSS, CoRL, NeurIPs etc.)
• Experience in embedded systems or distributed systems is a plus
• Experience in cloud computation and Cloud computing platforms (i.e. AWS, Azure, Google Cloud) is a plus
• Able to work independently, has strong research and problem-solving skills
• Good communication and teamwork skills.

Responsibilities

• Build up an advanced cloud-based system for sparse semantic scene understanding using VLMs.
• Architect a cloud-retrieval pipeline consisting of scene representation storage, localization and data retrieval, as well as VLM-based map creation.
• Implement the system using off-the-shelf building blocks for localization, mapping and communication, extending them where needed.
• Summarize research findings in high-quality paper and/or patent submissions.

Benefits

• Competitive hourly wage ranging from $41.00 to $68.00 based on various factors.
• Commitment to a diverse workforce and support for STEM initiatives.

What This Job Offers

• Job Type: Full-time
• Career Level: Intern
• Industry: Fabricated Metal Product Manufacturing
• Education Level: Master's degree
• Number of Employees: 10,001+ employees