ML Engineer, I - Acceleration Team

The mission of the Acceleration Team is to deploy trained Machine Learning Models on embedded hardware. This includes developing custom CUDA layers (usually guided by reference designs in Python) and implementing pre- and post-processing modules that convert raw data into model inputs and convert model outputs to usable signals. A major focus of the team is minimizing model inference latency by iteratively profiling and hand-tuning GPU kernels and C++ code.

• →Develop modern C++ and CUDA code for AI inference, including data processing algorithms and custom neural network layers
• →Optimize C++ and CUDA code guided by timing measurements and profiling to minimize processing latency
• →Utilize existing third-party and internal frameworks, libraries and tools
• →Work closely with other engineers and domain experts in a collaborative environment
• →Write functional and performance tests and documentation
• →Deliver high-quality, unit-tested, production code suitable for deployment in embedded, safety-critical environments 

• Bachelor’s degree in Computer, Electrical, or Software engineering, or advanced degree
• Deep understanding of memory management in C++, error handling, compilers and debuggers on Linux
• Understanding of mechanisms of calling C/C++ functions from Python
• Understanding of neural networks and machine learning
• Strong math skills including linear algebra
• Strong written and verbal technical communication skills
• Positive, team player mindset

• CUDA experience
• Experience with deep learning frameworks such as PyTorch or TensorFlow

At Torc, we’re committed to building a diverse and inclusive workplace. We celebrate the uniqueness of our Torc’rs and do not discriminate based on race, religion, color, national origin, gender (including pregnancy, childbirth, or related medical conditions), sexual orientation, gender identity, gender expression, age, veteran status, or disabilities. 
Even if you don’t meet 100% of the qualifications listed for this opportunity, we encourage you to apply. 

Our compensation reflects the cost of labor across several geographic markets. Pay is based on a number of factors and may vary depending on job-related knowledge, skills, and experience. Torc's total compensation package will also include our corporate bonus and stock option plan. Dependent on the position offered, sign-on payments, relocation, and other forms of compensation may be provided as part of a total compensation package, in addition to a full range of medical, financial, and/or other benefits.

Job ID: R-102569