Machine Learning Engineer

Abouttherole

Weareseekingahigh-impact,technicallydeepMachineLearningEngineertodevelop,optimize,anddeployproductionMLmodelsacrossourautonomousvehicle(AV)stack.Thisroleisidealforengineerswhoenjoybuildingmodelsend-to-end-fromdataandtrainingthroughoptimizationandreal-timedeploymentonautonomousvehicles.

You will work closely with perception, prediction, planning, infrastructure, systems, and hardware teams to ensure models are efficient, scalable, reliable, and production-ready for both on-vehicle and cloud workflows.

This role is onsite 5 days a week at our Santa Clara, CA office!

Whatyou’lldo

• End-to-EndModelDevelopment: OwnthefullMLlifecycle,includingdatastrategy,preprocessing,training,evaluation,optimization,deployment,andmonitoring.
• AutonomousDrivingModels: Developandimprovemodelssupportingperception,prediction,planning,andsceneunderstanding.
• EfficientNeuralNetworkDesign: Optimizemodelsusingtechniquessuchasquantization,pruning,sparsification,compression,andefficientarchitecturedesigntomeetstrictlatency,compute,memory,andpowerconstraints.
• Real-TimeDeployment: IntegratetrainedmodelsintoC++-basedautonomysystemsandoptimizeinferenceforproductionvehiclehardware.
• ModelOptimization: ProfileandoptimizeneuralnetworksusingCUDA,TensorRT,andrelatedtechnologies.
• SimulationandEvaluation: Analyzemodelperformanceusingsimulationandreal-worlddrivingdata,identifyfailuremodes,anddriveimprovements.
• ScalableMLInfrastructure: Buildhigh-throughputpipelinesfortraining,evaluation,dataprocessing,andlarge-scaleofflineinference.
• DataWorkflowsandTooling: Developreliablepipelinesfordatasetcuration,annotation,preprocessing,visualization,diagnostics,benchmarking,andcontinuousfeedbackfromfielddata.
• Cross-FunctionalIntegration: Partnerwithautonomy,systems,hardware,andinfrastructureteamstoensureMLcomponentsintegratereliablyintothebroadervehicleplatform.

Whatwe’relookingfor

• Education: MSorPhDinComputerScience,MachineLearning,Robotics,ElectricalEngineering,Statistics,Optimization,orarelatedfield.
• Experience: Opentoallexperiencelevels.Levelingwillbedeterminedbasedonexperienceandtechnicaldepth.
• Programming&Frameworks:
• StrongPythonskillsandexperiencewithframeworkssuchasPyTorchorTensorFlow.
• StrongC++skillsandexperienceintegratingMLmodelsintohigh-performanceproductionsystems.
• CoreML&SystemsExpertise:
• DeepunderstandingofMLworkflows,includingdatacuration,training,evaluation,ablationstudies,deployment,andinferenceoptimization.
• Experiencedeployingandoptimizingneuralnetworksforreal-time,embedded,robotics,autonomousdriving,orotherperformance-constrainedsystems.
• Experiencewithmodeloptimizationtechniquessuchasquantization,pruning,compression,andefficientarchitectures.
• Experiencewithsoftwarearchitecture,profiling,latencyoptimization,system-leveldebugging,anddataflowanalysis.
• Infrastructure&ComputeTools:
• ExperiencewithCUDAandTensorRTishighlydesirable.
• Experiencewithcloud-basedMLtrainingandevaluationpipelines,preferablyAzure.

BonusQualifications:

• Experiencewithtransformers,multimodalmodels,diffusionmodels,worldmodels,orend-to-enddrivingmodelsisaplus.
• Experienceinautonomousdriving,robotics,orothersafety-criticalreal-timeMLsystemsisstronglypreferred.
• PublicationsordemonstratedtechnicalcontributionsinefficientML,autonomousdriving,robotics,orrelatedareasareaplus.
• Priorcontributionstolarge-scaleMLsystemsdeployedinproduction.

SalaryRange $170,000-$240,000