Join TuSimple and help change the way the world moves. Together we're making freight transportation safer, more efficient, and more environmentally friendly.
Email you resume directly to: senior_software_engineer__ml_accelerator_gpu_programming_bfaabf522us@ivy.greenhouse.io
Company Overview
Come join a higher calling and find a deeper purpose!
As a multi-national Artificial Intelligence Technology Company, we are at the epicenter of the Autonomous Vehicle Universe. Our breakthroughs are leading the industry in autonomous trucking.
While inventing the framework of Autonomous Driving, our current fleet of autonomous Trucks are helping communities receive much-needed supplies and medical equipment around the clock. Our people are some of the most talented engineers and contributors who are leaving behind a historic legacy.
TuSimple was founded half a decade ago with the goal of bringing the top minds in the world together to achieve the dream of a driverless truck solution. With a foundation in computer vision, algorithms, mapping, and Artificial Intelligence, TuSimple is working to create the first global commercially viable Autonomous Freight Network.
Opportunity Overview:
As a multi-national Artificial Intelligence Technology Company, we are at the epicenter of the Autonomous Vehicle Universe. Our breakthroughs are leading the industry in autonomous trucking.
At TuSimple, the Heterogeneous Computing team is responsible for optimizing algorithm performance through hardware accelerators, improving accelerator utilization, as well as maintaining the stability of the whole system.
Example projects we are working on include:
- Accelerate existing algorithms using CUDA and GPU.
- Minimize hardware resource usage, e.g. GPU computing utilization and memory footprint
- Build GPU-accelerated Machine Learning Libraries.
- Conduct research on state-of-the-art GPU technologies.
Role Responsibilities:
- Analyze the system and identify potential GPU performance bottlenecks.
- Perform in-depth study of the working mechanism of CUDA and GPU, and apply them into existing applications properly.
- Improve the neural network inference speed with minimum hardware resource usage.
- Conduct research on various neural network acceleration techniques, and take the ideas from conception into production.
- Lead the team to design, develop and optimize GPU applications or libraries.
Experience & Skills Required:
- 3+ years of experience in GPU related fields.
- Solid understanding on Computer System/GPU Architecture.
- Excellent communication and interpersonal skills.
Preferred Skills and Experience:
- 2+ years of management experience
- Development experience in deep learning frameworks (MXNet, TensorFlow, PyTorch, TVM, TensorRT) and CUDA libraries (cuBLAS, cuDNN, CUB, Thrust).
- Familiarity with neural network acceleration approaches, such as network pruning, network quantization, network sparsity or other optimizations for embedded devices.
- Experience in arm-based embedded systems/Nvidia Drive products
- Proficiency in C++/Python
100% employer-paid healthcare premiums for you and your family
Work visa sponsorship available
Relocation assistance available
Breakfast, lunch, and dinner served every day
Full kitchens on every floor with unlimited snacks, drinks, special treats, fruits, meals, and more
Stock options / equity
Gym membership reimbursement
Monthly team building budget
Learning/education budget
Employer-paid life insurance
Employer-paid long and short disability
TuSimple is an Equal Opportunity Employer. This company does not discriminate in employment and personnel practices on the basis of race, sex, age, handicap, religion, national origin or any other basis prohibited by applicable law. Hiring, transferring and promotion practices are performed without regard to the above listed items.
Email you resume directly to: senior_software_engineer__ml_accelerator_gpu_programming_bfaabf522us@ivy.greenhouse.io