Applied Science Manager - Perception, Amazon Robotics

Applied Science Manager - Perception, Amazon Robotics

Job :  |  Services LLC

Do you want to create intelligent, adaptable robots with global impact? The Vulcan Stow team (https://(Use the "Apply for this Job" box below).) at Amazon Robotics builds high-performance, real-time robotic systems that can perceive, learn, and act intelligently alongside humans—at Amazon scale. We invent and deploy machine learning, optimization algorithms, and geometric reasoning models that empower robots to identify the best available placement opportunities, learn effective stow strategies, and continuously improve capacity utilization.

Our mission is to deliver robust, real-time 3D scene understanding that drives downstream manipulation decisions — spanning semantic occupancy prediction, multi-view 3D reconstruction, depth estimation, and panoptic segmentation. We hire and develop subject matter experts in 3D computer vision, deep learning, and generative modeling, targeting high-impact algorithmic unlocks in scene completion, shape reasoning, and edge-optimized inference.

We are seeking an experienced Applied Science Manager to lead the Perception team — a group of applied scientists and engineers pushing the frontier of 3D computer vision for robotics. You will drive technical vision using transformer-based architectures, generative 3D models, and scalable data pipelines to deliver sub-250ms perception outputs with the accuracy, robustness, and latency that production robots demand. Collaborating with cross-functional teams across match & affordances, motion planning, and fulfillment operations, you will ship models that run on real robots in real fulfillment centers.

• People Leadership:
  Prioritize being a great people manager — motivating, rewarding, and coaching your diverse team is the most important part of this role. Recruit and retain top talent in 3D computer vision, deep learning, and perception systems. Excel in day-to-day people and performance management tasks.
• Technical Vision:
  Set a vision for your team and create technical roadmaps focused on 3D scene understanding, semantic occupancy prediction, depth estimation, and multi-view fusion. Guide research, design, deployment, and evaluation of perception models — including encoder-decoder networks, query-based transformers, and generative architectures — that produce actionable 3D representations for downstream robot decision-making.
• Cross-functional Collaboration:
  
  Work closely with match & affordances, motion planning, hardware, and fulfillment teams to deliver integrated perception solutions that are robust to occlusion, clutter, and sensor noise. Partner with ML infrastructure teams on scalable training pipelines, pseudo-ground-truth data generation, and edge deployment optimization.
• Delivery Excellence:
  Implement best practices in applied research and software development. Manage project timelines, resources, and deliverables effectively. Keep technical skills current to contribute meaningfully to architecture decisions, model reviews, and inference optimization discussions.
• Problem Solving:
  Regularly participate in deep-dive troubleshooting exercises and drive technical post-mortem discussions to identify root causes of perception regressions, model failures, depth/segmentation misalignments, and latency degradations.

• Prioritize being a great people manager: motivating, rewarding, and coaching your diverse team is the most important part of this role. You will recruit and retain top talent and excel in people and performance management tasks.
• Set a vision for the team and create the technical roadmap that deliver results for customers while thinking big…