At Deeplite, we are tackling inference optimization of deep neural networks, making them faster and energy-efficient from cloud to edge computing. Our solution leverages state-of-the-art technology from elite universities to make deep neural networks applicable for any device, and our team works hard on the iterative evolution of the science behind deep neural networks to directly improve daily life.
Our Inference Engine team is growing and we’re looking to hire a Deep Learning Inference and Compiler Engineer.
Here’s what you’ll be doing:
- You will be working on cutting edge problems in Deep Learning for Deeplite optimization software stack.
- Work on architecture-specific neural network optimization algorithms for high performance computing.
- Design and develop a lightweight and high-performance inference engine for CPUs and microcontrollers.
- In this role you will have opportunity to develop an inference engine running on many devices.
Here’s what we need you to bring to the table:
- Bachelors, Masters or Ph.D. or equivalent in Computer Science, Computer Engineering, or related field.
- 4+ years of relevant work or research experience in high performance computing and compiler optimizations.
- Excellent C/C++ programming and software design skills, including debugging, performance analysis, and test design.
- Excellent Python skills, and a dedication to writing clean, understandable, testable code with an eye towards maintainability.
- Experience with optimizing compiler, programming low-level hardware and microcontrollers.
- Experience with the following technologies is a huge plus: TVM, LLVM, ARM-NN, CMSIS-NN, RISC-V, ARM, OpenCL, deep learning models and algorithms, and deep learning framework design.