Applied Scientist- Physical AI for Manufacturing, OMHS SCS
# Applied Scientist- Physical AI for Manufacturing, OMHS SCS **Amazon.com Services LLC - A57** · Boston, Massachusetts, USA · `On-site` · `full-time` 🕒 **Статус:** *Опубликовано: сегодня* · *Источник: Amazon* --- ### Top Skills & Match 🎯 **Ключевой стек роли:** `[Applied Science]` `[Applied Science]` --- ### About the Role As an Applied Scientist on the OMHS Software Controls and Science team, you will build and deploy first-of-its-kind physical AI capabilities within Amazon Manufacturing Services. You will turn applied research into functional prototypes and production systems that operate on real parts under real shop floor conditions. This role combines applied ML, 3D perception, and geometric reasoning with a strong manufacturing-outcome focus. It will be your job to frame ambiguous fabrication problems as tractable scientific problems, and to deploy perception and part-recognition systems on robotic welding cells that match physical parts to their CAD models an determine orientation, tooling, and fixturing without manual programming. You will own the full loop from prototype to measurable result: instrumenting robotic cells with sensors, collecting real-world manufacturing data, training and iterating models against accuracy and cycle-time targets, and integrating your work into robot motion planning and production software pipelines. Your near-term mission is to help enable a lossless digital thread from engineering specification to autonomous robotic execution, starting with welding, in a high-mix environment scaling toward high-volume production. Key job responsibilities • Deploy 3D perception and part-recognition systems on robotic welding cells that match physical parts to their CAD models and determine part orientation, tooling, and fixturing without manual programming. • Build software pipelines that connect CAD and engineering-drawing interpretation to robot motion planning and execution in a production manufacturing environment. • Frame ambiguous fabrication problems as tractable scientific problems, and prototype solutions end to end — from sensor setup and data collection to model training, deployment, and performance evaluation. • Evaluate, recommend, and integrate commercial robotic platforms, 3D scanning systems, and sensor hardware to support physical AI development on the shop floor. • Instrument robotic cells, collect real-world manufacturing data, and iterate on model performance against measurable accuracy and cycle-time targets. • Collaborate across automation engineering and software engineering teams to integrate your solutions into the shop floor deployment architecture. About the team Amazon is building next generation software, hardware, and processes that will run our global network of fulfillment centers that move millions of units of inventory, and ensure customers get what they want when promised. The Science Software team in the One MHS organization unlocks Material Handling Equipment (MHE) innovation through a multiplicity of disciplines within Artificial Intelligence (AI) and applied science, including Computer Vision (CV), Physics-Informed Neural Networks (PINNs), Optimization, Reinforcement Learning, classical Machine Learning, statistical modeling, and sensing-hardware prototyping. Rooted in first principles aligned experimentation, the team is dedicated to building self-optimizing fulfillment centers, developing the models that drive real-time, building-wide orchestration of MHE. We conduct experiments, develop models, and apply machine learning (ML) at scale to optimize throughput, flow, merge, and congestion control, and to improve operational performance across the fulfillment network. - PhD in engineering, technology, computer science, machine learning, robotics, operations research, statistics, mathematics or equivalent quantitative field - 1+ years of deep learning, computer vision, human robotic interaction, algorithms implementation experience - Hands-on experience deploying robots or autonomous systems in real-world environments. - Ability to debug the full stack from perception to control.
- Applied Science
- Applied Science
Наблюдалась 2026-09-25, впервые 2026-09-25, источник — Amazon.