✦ Luna Orbit — AI & Machine Learning

Interdisciplinary Sys Engineer, GES NA Ops Engineering

at Amazon.com

📍 US, WA, Bellevue Unknown Posted April 14, 2026
Type Not Specified
Experience senior
Exp. Years Not specified
Education Not specified
Category AI & Machine Learning

Amazon is seeking an interdisciplinary Computer Vision & Automation Engineer to design and deploy intelligent automation systems across fulfillment networks. The role focuses on end-to-end integration of cameras, sensors, edge computing, and control interfaces to deliver real-time operational intelligence.

  • Lead end-to-end deployment of computer vision-enabled automation systems
  • Design and develop integrated systems combining cameras, sensors, edge compute devices, and control interfaces
  • Bridge AI/ML models with physical systems for low-latency inference
  • Own hardware-software integration including device selection, network configuration, connectivity to cloud or on-prem systems
  • Integrate with controls systems (PLCs, industrial protocols) for closed-loop automation and execute system validation

This role bridges AI/ML models with physical automation by enabling reliable data capture, processing pipelines, and low-latency inference on industrial equipment. You will integrate with controls systems such as PLCs and industrial protocols, validate performance using test plans and field trials, and implement safety, privacy, and reliability safeguards.

The ideal candidate is an interdisciplinary engineer who has built production-grade automation systems using computer vision and edge computing. They can bridge AI/ML models into physical hardware by designing low-latency data pipelines, integrating with sensors and cameras, and connecting systems to controls (PLCs and industrial protocols) with strong validation and safety practices.

computer visionautomationedge computinghardware-software integrationAI/ML modelslow-latency inferenceintegration with controls systems (PLCsindustrial protocols)computer vision model productionizationsystem validation strategies including test plansfield trialsand performance benchmarking
device selectionnetwork configurationconnectivity to cloud or on-prem systemssafety/privacy implementation with data filtering and maskingprototyping and scale custom hardware and automation solutions
cloud or on-prem systemsPLCindustrial protocols
computer visionautomationreal-time operational intelligenceedge computingphysical automation systemshardware systemsembedded/edge computingsensor-driven automation solutionscamerassensorsedge compute devicescontrol interfacesAI/ML modelsdata captureprocessing pipelineslow-latency inferencehardware-software integrationdevice selectionnetwork configurationconnectivity to cloud or on-prem systemsproductionizing computer vision modelsrobustnessscalabilityperformance benchmarkingtest plansfield trialsintegration with controls systemsPLCsindustrial protocolsclosed-loop automationsafetyprivacyreliabilitydata filteringmaskingfail-safe system behaviorprototyping custom hardwarestandardization of architecturesdeployment patternsengineering best practicesartifact
computer visionautomationreal-time operational intelligenceedge computingphysical automation systemshardware systemsembedded/edge computingsensor-driven automation solutionscamerassensorsedge compute devicescontrol interfacesAI/ML modelsdata captureprocessing pipelineslow-latency inferencehardware-software integrationdevice selectionnetwork configurationconnectivity to cloud or on-prem systemsproductionizing computer vision modelsrobustnessscalabilityperformance benchmarkingtest plansfield trialsintegration with controls systemsPLCsindustrial protocolsclosed-loop automationsafetyprivacyreliabilitydata filteringmaskingfail-safe system behaviorprototyping custom hardwarestandardization of architecturesdeployment patternsengineering best practicesartifact (researchschematicsspecificationsprototypes3D Modelsanalysistest plansstrategic narrativesetc.)
communicate ideas effectivelycollaborate with scientistscollaborate with controls engineerscollaborate with operations teamscross-functional collaborationpartnering closelyseeking diverse perspectiveslistening to feedbackwilling to change directionbuild consensuslead resolution of contentious issues
Industry E-commerce
Job Function Build production-grade computer vision and edge-enabled automation systems integrated with industrial controls.
Role Subtype Computer Vision Engineer
Tech Domains Amazon Web Services, AI & Machine Learning, Edge Computing, Internet of Things
Interdisciplinary Sys EngineerComputer Vision & Automation Engineercomputer visionautomationedge computingembedded/edge computinghardware-software integrationAI/ML modelslow-latency inferencesensor-driven automation solutionscamerassensorsedge compute devicescontrol interfacesPLCsindustrial protocolsclosed-loop automationtest plansfield trialsperformance benchmarkingdata filteringmaskingfail-safe system behavior

No experience with computer vision and AI/ML model productionization, No experience integrating automation systems with PLCs and industrial protocols, No experience running system validation with test plans and field trials

Apply for this Position →

Get matched to jobs like this

Luna finds roles that fit your skills and career goals — no endless scrolling required.

Create a Free Profile