Parking Perception DNN Engineer

Details

Intelligent machines powered by Artificial Intelligence computers that can learn, reason and interact with people are no longer science fiction. GPU Deep Learning has provided the foundation for machines to learn, perceive, reason and solve problems. NVIDIA’s GPU runs Deep Learning algorithms, simulating human intelligence, and acts as the brain of computers, robots and self-driving cars that can perceive and understand the world.

As a member of the perception team you will develop and productize NVIDIA's autonomous driving solutions. You will work on building world-class 3D obstacle perception solutions based on multi-sensor fusion (cameras, ultrasonic sensors, radar) to estimate high-resolution reconstruction of the world (e.g., occupancy networks). The primary approach will be deep learning. You will be challenged to improve robustness and accuracy as well as efficiency of the solutions to fully enable autonomous driving anywhere and anytime.

Responsibilities

• Develop multi-sensor-fusion based deep learning models for obstacle perception and fusion in complex driving environments.
• Conduct applied research and R&D of deep learning and multi-sensor fusion algorithms to improve accuracy of 3D obstacle perception, focusing on high-resolution world reconstruction (e.g., occupancy networks).
• Identify and analyze strengths and weaknesses of 3D perception solutions using large-scale benchmark data (real and synthetic); build KPIs and iteratively optimize models. Includes data verification, model architecture design, loss function engineering, and debugging ML issues.
• Productize perception solutions to meet product requirements for safety, latency, and software robustness, emphasizing production-grade deep learning model development.
• Drive data-driven development by working with data collection and labeling teams: prioritize data collection and labeling to maximize data value.

Requirements

• 10+ years of hands-on experience developing deep learning and algorithms for sophisticated real-world problems.
• Proficiency in deep learning frameworks (example: PyTorch).
• Experience in multi-sensor fusion (cameras, ultrasonic sensors, radar) for perception tasks, particularly high-resolution world reconstruction.
• Proven experience in production deep learning model development, including data verification, model architecture design, loss function engineering, and debugging ML models.
• Experience in data-driven development and collaboration with data and ground-truth teams.
• Strong programming skills in Python and/or C++.
• BS/MS/PhD in Computer Science, Electrical Engineering, sciences or related fields (or equivalent experience).
• Outstanding communication and teamwork skills.

Ways to stand out

• Experience in end-to-end deep learning model development.
• Proven expertise in perception solutions for autonomous driving or robotics using multi-sensor deep learning.
• Hands-on experience developing and deploying DNN-based solutions to embedded platforms for real-time applications.
• Good understanding of 3D computer vision fundamentals, camera calibrations (intrinsic and extrinsic), and sensor fusion principles.
• Experience with CUDA and ability to implement CUDA kernels as part of training or inference pipelines.

Compensation & Benefits

• Base salary ranges (determined by location, experience, and comparable employees):
  • Level 4: 184,000 USD - 287,500 USD
  • Level 5: 224,000 USD - 356,500 USD
• Eligible for equity and benefits (link to NVIDIA benefits provided in original posting).

Other information

• Applications accepted at least until March 14, 2026.
• This posting is for an existing vacancy.
• NVIDIA uses AI tools in its recruiting processes.
• NVIDIA is an equal opportunity employer and committed to fostering a diverse work environment.