As a Senior Perception Engineer at NVIDIA, you will join our cutting-edge team focused on developing autonomous driving solutions using deep learning and multi-sensor fusion technologies. Your daily tasks will involve creating robust 3D obstacle perception systems that integrate data from cameras, ultrasonic sensors, and radar to enhance vehicle safety and performance in complex environments. You’ll leverage frameworks like PyTorch to develop innovative algorithms, optimize model accuracy through iterative testing with large datasets, and ensure production readiness by addressing latency and software robustness concerns. Additionally, you will collaborate closely with data collection teams to maximize the value of input data for continuous improvement. This role requires extensive experience in deep learning development, multi-sensor fusion, and embedded platform deployment, along with strong programming skills in Python or C++.
Skills
PyTorch
Python
C++
CUDA
DeepLearning
MultiSensorFusion
3DComputerVision
CameraCalibration
SensorFusion
DataVerification
LossFunctionEngineering
MLOps
EmbeddedSystems
RealTimeApplications
KPIBuilding
LargeScaleBenchmarking
DataCollectionPrioritization
LabelingPrioritization
What you'll do
Develop deep learning models for multi-sensor fusion based obstacle perception in autonomous driving.
Improve accuracy and robustness of 3D obstacle perception solutions through iterative KPI optimization.
Productize perception solutions, ensuring safety, low latency, and software robustness in production.
Collaborate with data teams to prioritize and plan high-value data collection and labeling for accuracy improvements.
Debug and refine deep learning models using detailed analysis of loss functions and model architecture.
What we're looking for
Over 10 years of experience developing deep learning algorithms for complex real-world problems using frameworks like PyTorch.
Expertise in multi-sensor fusion (cameras, ultrasonic sensors, radar) for high-resolution world reconstruction and obstacle perception.
Proficiency in production-level deep learning model development, including data verification, architecture design, loss function engineering, and debugging.
Strong background in data-driven development, collaborating with data collection and labeling teams to enhance system accuracy.
Excellent programming skills in Python and/or C++, with hands-on experience deploying DNN solutions on embedded platforms for real-time applications.
BS/MS/PhD in CS, EE, sciences or related fields (or equivalent experience).
Experience developing perception solutions for autonomous driving using deep learning with multi-sensor input.
Market check
Salary context
This
$184,000–$287,500
range sits above
65%
of similar postings on FindRole.
Peer median band
$170,750–$259,375
Median floor and ceiling across peers.
Typical midpoint (25–75%)
$167,500–$248,375
Middle half of comparable postings.
Based on 240 comparable postings.*
* 240 is the maximum number of comparable postings sampled.
Employer
About Nvidia
Nvidia is a leading designer of graphics processing units (GPUs) and system-on-chip units, powering gaming, professional visualization, data centers, and artificial intelligence workloads. Industry: Semiconductors & AI Computing
Nvidia currently has
801 open roles
on FindRole.
Listed pay typically runs
$184,000–$287,500
across 797 roles with salary data.
Us, Ca, Santa Clara, US66 days ago
$184,000–$287,500
C++
CUDA
ROS
Radar
Lidar
Camera
Ultrasonic sensors
Data association algorithms
Sensor fusion
Multi-view geometry
Occupancy grid tracking
CI/CD
Git
Linux