Embodied AI Engineer
$150,000–$210,000 year
HybridEnglewood Cliffs, New Jersey, United States
Job Summary
Implement, debug, and optimize model architectures (VLA, diffusion/flow-matching policies, world models) taking them from prototype to reliable and reproducible systems. Build and maintain scalable training and evaluation infrastructure for Robot Foundation Models and on-robot deployment stacks. Architect and operate large-scale data pipelines that combine high-fidelity simulation, generative AI, teleoperation, and real-world data collection. Work hands-on with robot hardware to bring up new platforms, debug real-world failures, and close the loop between simulation and deployment. Collaborate with global research teams and hardware partners to integrate embodied AI systems into LG's consumer ecosystem and contribute engineering input to technical roadmaps. This hybrid role at LG's Emerging Technology Lab designs the foundation for the Zero-labor Home by turning generalist robot intelligence into deployable capability on next-generation LG home robot platforms.
Required Qualifications
- Bachelor's degree and 5+ years of relevant industry and/or research experience, or Master's degree and 3+ years of relevant industry and/or research experience, in Computer Science, Mechanical Engineering, Electrical Engineering, or a related technical field
- PhD preferred but not required
- Strong software engineering proficiency in Python or C++, experience working across the full stack from data pipeline to deployed model
- Hands-on experience with one or more of the following: Training and deploying Robot Foundation Models (e.g., VLA, diffusion/flow-matching policies for manipulation or locomotion), Building data pipelines for robot learning (simulation, teleoperation, generative data augmentation), Developing and maintaining robot system infrastructure for robot manipulators or mobile robots, RGB/Depth cameras, FT/tactile sensors
- Excellent written and verbal communication skills, with the ability to work closely with research scientists and translate ideas into shipped systems
Desired Qualifications
- Familiarity with the robot learning research literature (world models, spatial intelligence, learning from demonstration) sufficient to collaborate closely on architecture decisions
- Contributions to open-source robotics or ML infrastructure tooling
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.