Robot Intelligence Research Engineer

Samsung Research America

Mountain View (CA)

On-site

USD 163,600 - 324,500

Full time

14 days+

Application generator

Turn this role into an interview — a resume and cover letter built around what this employer wants.

Get past ATS filters

Benefits offered by this job

Competitive compensation

Excellent benefits

On-site in Mountain View

Job summary

Samsung Research America’s Robot Intelligence Lab in Mountain View invites researchers and engineers at Senior, Staff and Senior Staff levels to join a growing team focused on robotics and embodied intelligence. You will work across groups such as Reasoning, Dexterity, Data Efficiency and Robot Systems to advance state-of-the-art robotics technologies.

The role emphasizes design, integration, and evaluation of robotic perception, planning, and control algorithms, with opportunities to publish

Qualifications

PhD or Master’s degree in EECS/Robotics or equivalent combination of education, training, and experience.
2-14+ years’ experience in state-of-the-art robotics R&D, such as task-and-motion planning, VLA models, open-world 3D perception, trajectory prediction, MD control, RL, multimodal information fusion, and whole-body control.
Demonstrated experience in sensing, kinematics, dynamics, and control systems on real robots.
Solid understanding of computer vision techniques (object detection, segmentation, tracking) and multi-view image processing.
Knowledgeable of tools and processes to monitor ML model performance and data quality, including model tuning experience.
Familiarity with PyTorch, TensorFlow, C++, ROS, and CUDA.
Demonstrated experience in software engineering best practices to track, communicate, and document progress.
Strong robotics fundamentals including locomotion, manipulation, pose tracking, 3D mapping, SLAM, ROS, and policy architectures for semi/unstructured environments.
Excellent problem-solving and communication skills.

Responsibilities

Design and evaluate robotic hardware, sensors, and software for semi-structured/unstructured environments.
Integrate sensors and actuators into proof-of-concept robotic systems and optimize performance.
Develop and test algorithms for perception, control, learning, navigation, and manipulation.
Create virtual models and simulations using system identification, real-to-sim, and sim-to-real techniques.
Develop data collection, processing, and model management for in-the-wild data.
Collaborate with cross-functional teams from concept to completion.
Document and present results evaluating algorithms on target compute platforms.
Conduct pilot studies and formal experiments to benchmark against state-of-the-art approaches.
Maintain fleets of robots and infrastructure for logging and monitoring.