Applied Science Manager - Match & Affordances, Amazon Robotics

Amazon Amazon · Big Tech · Seattle, WA · Machine Learning Science

This role manages a team of applied scientists and engineers focused on developing ML and RL algorithms for robotic systems to optimize stow strategy and warehouse capacity. It involves leading research, design, deployment, and evaluation of these systems, with a focus on transformer architectures, affordance learning, and geometric reasoning in high-density environments.

What you'd actually do

  1. Prioritize being a great people manager - motivating, rewarding, and coaching your diverse team is the most important part of this role.
  2. Set a vision for your team and create technical roadmaps focused on stow policy development, placement optimization, and density improvements.
  3. Guide research, design, deployment, and evaluation of ML and RL algorithms, optimization methods, and geometric reasoning systems that inform robot action selection.
  4. Work closely with perception, motion planning, hardware, and fulfillment teams to create integrated solutions that maximize storage density while maintaining operational reliability.
  5. Implement best practices in applied research and software development. Manage project timelines, resources, and deliverables effectively.

Skills

Required

  • PhD, or Master's degree and 4+ years of industry or academic research experience
  • 6+ years of applied research experience
  • 3+ years of scientists or machine learning engineers management experience
  • Experience building machine learning models or developing algorithms for business application
  • Experience with deep learning libraries such as PyTorch, TensorFlow, MxNet
  • Research publications in computer vision, deep learning or machine learning at peer-reviewed workshops, conferences or journals
  • Knowledge of engineering practices and patterns for the full software/hardware/networks development life cycle, including coding standards, code reviews, source control management, build processes, testing, certification, and livesite operations

Nice to have

  • Experience hiring and growing top talent
  • Experience in representation learning, and reinforcement learning in robotics systems.
  • Familiarity with the developments in the VLAs, VLMs, affordance learning

What the JD emphasized

  • Prioritize being a great people manager
  • Recruit and retain top talent
  • Guide research, design, deployment, and evaluation of ML and RL algorithms
  • Partner with computer vision teams on 3D scene understanding and container geometry representation that drives policy learning

Other signals

  • lead a team of talented applied scientists and engineers
  • drive ML innovation using the latest advancements in transformer-based architectures
  • enable maximum storage utilization, learn affordances and behaviors in high-density environments
  • deliver scalable solutions that optimize stow strategy and warehouse capacity