Senior Machine Learning Engineer, Perception - Autonomous Driving
Tech Stack
Tag name is followed by "@" symbol and proficiency level value.
About proficiency levels:
- 1-2 — basic awareness. Minimal hands-on experience, and a rudimentary understanding of the technology's purpose;
- 3-6 — daily use. Comfortable and regular usage, capable of handling common tasks and challenges related to the technology;
- 7-9 — you are an expert, you can teach others, you know all the pitfalls and tricks;
- 10 — exceptional knowledge, comprehensive understanding, and adeptness in all aspects of the technology, including advanced problem-solving. Think twice before claiming or demanding such level.
AI
Algorithms @ 4
Communication @ 6
Deep Learning @ 4
GPU
Leadership @ 1
PyTorch @ 6
Python @ 7
Robotics @ 6
Technical Leadership @ 1
- 1-2 — basic awareness. Minimal hands-on experience, and a rudimentary understanding of the technology's purpose;
- 3-6 — daily use. Comfortable and regular usage, capable of handling common tasks and challenges related to the technology;
- 7-9 — you are an expert, you can teach others, you know all the pitfalls and tricks;
- 10 — exceptional knowledge, comprehensive understanding, and adeptness in all aspects of the technology, including advanced problem-solving. Think twice before claiming or demanding such level.
Details
Intelligent machines powered by artificial intelligence can learn, reason, and interact with people. NVIDIA's GPU deep learning technology provides the foundation for machines to perceive, reason, and solve problems in computers, robots, and self-driving cars.
The perception team is developing and productizing NVIDIA's autonomous driving solutions. This role will drive end-to-end solutions for perception modules responsible for online mapping, including road layouts, lane structures, boundaries, crosswalks, and other traffic components critical for driving without reliance on HD maps. The work focuses on improving robustness, accuracy, and efficiency to enable autonomous driving anywhere and anytime.
Responsibilities
- Design end-to-end solutions for the perception and autonomous vehicle stack to enable road network detection across diverse driving environments, from complex intersections and rural curved roads to multi-level highways.
- Conduct applied research and development of innovative deep learning models for lane graph construction, road boundary detection, traffic element recognition, and other static-world tasks.
- Develop generalizable approaches to support diverse operational design domains and country or regional expansion.
- Drive and prioritize data-driven development in collaboration with large data collection and labeling teams.
- Plan data collection and labeling priorities and optimize labeling efficiency to maximize the value of data.
- Leverage data simulation and augmentation to address extreme scenarios.
- Productize perception solutions while meeting requirements for safety, latency, and software robustness.
Requirements
- PhD with 4+ years of relevant experience, MS with 6+ years, or BS or equivalent experience with 8+ years in Computer Science, Computer Engineering, or a related technical field.
- Hands-on experience developing deep learning and algorithms to solve sophisticated real-world problems.
- Proficiency with deep learning frameworks such as PyTorch.
- Experience with data-driven development and collaboration with data and ground-truth teams.
- Strong programming skills in Python and/or C++.
- Outstanding communication and teamwork skills.
- Two or more years of technical leadership experience involving significant technical and organizational complexity is a plus.
Preferred Qualifications
- Expertise developing generalizable perception solutions for autonomous driving or robotics using deep learning with cameras.
- Experience developing and deploying DNN-based solutions to embedded platforms for real-time applications.
- Deep learning expertise supported by technical publications in leading conferences or journals.
- Expertise with Transformers, BEV architectures, and modern static-world perception techniques.
- Experience with online mapping and complex road detection problems.
Benefits
- Equity and employee benefits.
- NVIDIA is an equal opportunity employer committed to an inclusive work environment.
Applications will be accepted at least until August 22, 2026. This posting is for an existing vacancy. NVIDIA uses AI tools in its recruiting processes.