Boston Dynamics
Machine Learning Research Scientist - Atlas Perception
Boston Dynamics, Waltham, Massachusetts, United States, 02254
Do you have a passion for applying state-of-the-art deep learning techniques to solve real problems in robotics? As a
Research Scientist
on the Atlas Perception team, you will play a key role solving the uniquely challenging perception problems in humanoid robotics, including scene understanding, localization, object pose estimation, and terrain prediction. You will work closely with software, mechanical, and electrical engineers to research, develop, and test new robot technologies for Atlas and other R&D efforts at Boston Dynamics. As a leader in the field, you will shape novel ML perception techniques to drastically improve the utility of mobile robots by enabling them to effectively interact with the world around them.How You Will Make An Impact
Identify high impact areas where deep learning can be applied to solve real problems for our robotsResearch and evaluate new ML architectures to solve novel vision problemsTrain and adapt existing machine learning architectures for visual scene understandingCreate real and synthetic training datasets for ML modelsGuide and participate in ML infrastructure software engineering projectsRegularly disseminate research within the Atlas team and in wider company meetingsWe Are Looking For
Competence in Python programming and popular ML frameworksExperience researching and developing new ML architectures3+ years working on ML with robotics applications (academic research or industry)Additional Desired Experience
Experience with large-scale ML training infrastructureExperience training and evaluating ML models for visual scene understanding, for example:Object detection/semantic segmentationDepth estimation/completionVisual odometry/SLAMTerrain predictionGrasp estimationHands-on robot experienceCompetent with C++ programmingPractical knowledge of 3D geometry, projective geometry, camera modelsExperience with robot simulation software (for example: Gazebo, MuJoCo, Bullet, Unity, etc.)Experience or research in visual SLAMFamiliarity with typical robotics sensors and calibration procedures3D sensors: ToF, structured light, stereoRGB cameras and photographyIMUsExperience with real and synthetic dataset captureExperience with computer graphics (blender, procedural generation)
#J-18808-Ljbffr
Research Scientist
on the Atlas Perception team, you will play a key role solving the uniquely challenging perception problems in humanoid robotics, including scene understanding, localization, object pose estimation, and terrain prediction. You will work closely with software, mechanical, and electrical engineers to research, develop, and test new robot technologies for Atlas and other R&D efforts at Boston Dynamics. As a leader in the field, you will shape novel ML perception techniques to drastically improve the utility of mobile robots by enabling them to effectively interact with the world around them.How You Will Make An Impact
Identify high impact areas where deep learning can be applied to solve real problems for our robotsResearch and evaluate new ML architectures to solve novel vision problemsTrain and adapt existing machine learning architectures for visual scene understandingCreate real and synthetic training datasets for ML modelsGuide and participate in ML infrastructure software engineering projectsRegularly disseminate research within the Atlas team and in wider company meetingsWe Are Looking For
Competence in Python programming and popular ML frameworksExperience researching and developing new ML architectures3+ years working on ML with robotics applications (academic research or industry)Additional Desired Experience
Experience with large-scale ML training infrastructureExperience training and evaluating ML models for visual scene understanding, for example:Object detection/semantic segmentationDepth estimation/completionVisual odometry/SLAMTerrain predictionGrasp estimationHands-on robot experienceCompetent with C++ programmingPractical knowledge of 3D geometry, projective geometry, camera modelsExperience with robot simulation software (for example: Gazebo, MuJoCo, Bullet, Unity, etc.)Experience or research in visual SLAMFamiliarity with typical robotics sensors and calibration procedures3D sensors: ToF, structured light, stereoRGB cameras and photographyIMUsExperience with real and synthetic dataset captureExperience with computer graphics (blender, procedural generation)
#J-18808-Ljbffr