Embodied AI Researcher

What we can offer:

A crafted employee experience designed to foster professional growth, a focus on health & well-being and an internal community that will set you up for success.

We offer an environment that enables colleagues to demonstrate their capabilities, focus on their work and create value. At LG, you're encouraged to take a creative and individual approach to challenges with strong emphasis placed on performance and skill-and equal, merit-based opportunities across the board. We want our colleagues to grow with our global business. That's why we deliver sure rewards for exceptional performance and offer industry-leading benefits. Come join the team!

The Opportunity:

LG's Emerging Technology team is the catalyst for technological innovation within LG's CTO organization. Located in the Silicon Valley and New Jersey, we drive excellence across CTO organizations and business units by pioneering in select emerging technology areas. As the Center of Excellence (CoE), we define and shape key technology domains, setting strategic directions that foster impactful internal and external partnerships to deliver measurable business value.

Our Emerging Technology team is looking for an Embodied AI Researcher with strong academic and/or industry experience. This is a hybrid position based out of LG North America HQ at Englewood Cliffs, NJ (15 mins from New York City). As an Embodied AI Researcher, you will contribute to the development of physical intelligence for deploying robots for real-world tasks. Specifically, the ideal candidate should have solid experience and interest in topics such as building AI models for spatial intelligence and robot dexterity, leveraging simulation and large-scale data for task generalization, and integrating large foundation models for embodied AI applications. Your contributions will have a significant impact on LG's technology and product roadmaps.

In this role you will perform fundamental and applied research to push the scientific and technological frontiers of Embodied AI and Robotics on topics such as robot foundation model, self-supervised representation learning, large behavior models, multimodal spatial reasoning and action policy, and long-horizon task planning.

• Invent and integrate systems and pipelines for large-scale data generation through simulation, GenAI, and real-world demos for developing foundational embodied AI models leveraging a variety of modalities (images, video, text, audio, tactile, etc.).
• Develop and demonstrate foundational robot capabilities such as 3D spatial understanding, robot dexterity, task generalization and adaptation, and human-robot interaction and safety.
• Work with cross-functional teams to train, optimize, and deploy embodied AI models on integrated hardware-software platforms for home robot applications.
• Collaborate with HQ and 3rd-party research labs for integration of state-of-the-art AI models and robotics products into LG ecosystems.
• Contribute to defining project scope and goals to ensure alignment with business objectives.
  
  

Qualifications:

• PhD degree (or Master's degree with minimum 3 years of experience) in CS/Robotics/EE or similar field.
• 0~3 years of industry experience in embodied AI, robot perception, machine learning, robot action planning and control, physics simulation etc.
• Strong research experience in topics such as imitation learning, multimodal (images, text, audio, tactile, etc.) representation learning, self-supervised and reinforcement learning, 3D scene understanding and reconstruction, LLM/VLM fine-tuning and integration, task-and-motion planning.
• Hands-on experience of integration and evaluation of AI models with real-world data from RGB/depth/LIDAR sensors and on physical systems such as robot manipulators and mobile robots and etc.
• Good understanding of recent development trends in robot foundation models, vision-language-action models, vision foundation models, large behavior models, visuotactile policy learning, etc.
• Familiarity with physics simulation platforms and environments (e.g. PyBullet, MuJoCo, Nvidia Omniverse/Isaac Gym, Genesis) for large scale data generation and experimentation.
• Excellent verbal and writing skills to effectively present the derived results and technical concepts of developed methods.
• Strong interpersonal skills with the ability to effectively work with cross-functional teams.
  
  

#L1-JH1

#L1-Hybrid