Applied Scientist: Physical AI for Robotic Welding

Amazon; Boston (MA); On-site; USD 143,000 - 193,000; Full time

Benefits offered by this job

Health insurance

401(k) matching

Paid time off

Parental leave

Restricted stock units (RSUs)

Job summary

Amazon's OMHS Software Controls and Science team seeks an Applied Scientist to build first-of-its-kind physical AI capabilities on shop floor welding cells, turning research into prototypes and production systems that align parts to CAD models and determine orientation, tooling, and fixturing without manual programming.

You will own end-to-end deployments from sensors to model training and integrate with robot motion planning and production software, partnering with automation and software

Qualifications

• PhD in engineering, technology, computer science, machine learning, robotics, OR statistics or equivalent.
• 1+ years of deep learning, computer vision, HRI, 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.

Responsibilities

• Deploy 3D perception and part-recognition systems on robotic welding cells that match parts to CAD models and determine orientation and fixturing.
• Build software pipelines connecting CAD interpretation to robot motion planning and execution in production.
• Prototype end-to-end solutions from sensor setup to model training, deployment, and evaluation.
• Evaluate and integrate robotic platforms, 3D scanning, and sensor hardware for shop-floor AI development.
• Instrument robotic cells, collect manufacturing data, and iterate model performance against targets.
• Collaborate with automation and software teams to integrate solutions into deployment architecture.

Skills

Deep learning

Computer vision

Robotics

Algorithms implementation

Education

PhD in engineering or related quantitative field

Tools

Robotic manipulation platforms

Sensor fusion systems

Job description

Amazon's OMHS Software Controls and Science team seeks an Applied Scientist to build first-of-its-kind physical AI capabilities on shop floor welding cells, turning research into prototypes and production systems that align parts to CAD models and determine orientation, tooling, and fixturing without manual programming.

You will own end-to-end deployments from sensors to model training and integrate with robot motion planning and production software, partnering with automation and software