d-Matrix is a computing platform that targets artificial intelligence inferencing workloads in the datacenter. They are seeking a Compiler Software Engineer Intern to develop software for logical-to-physical mapping in their compiler, focusing on managing floating point data types and collaborating with engineering teams.
Responsibilities
Design, implement and evaluate a method for managing floating point data types in the compiler
Engage and collaborate with engineering team in the US to understand the mechanisms made available by the hardware design to perform efficient floating point operations using reduced precision floating point data types
Demonstrate successful completion of the project by a simple model output by the compiler incorporating the your code that executes correctly on the hardware instruction set architecture (ISA) simulator
Qualification
Required
Bachelor’s degree in computer science or equivalent 3 years towards an Engineering degree with emphasis on computing and mathematics coursework.
Proficiency with C++ object-oriented programming is essential.
Understanding of fixed point and floating-point number representations, floating point arithmetic, reduced precision floating point representations and sparse matrix storage representations and the methods used to convert between them.
Some experience in applied computer programming (e.g. prior internship).
Understanding of basic compiler concepts and methods used in creating compilers (ideally via a compiler course).
Data structures and algorithms for manipulating directed acyclic graphs.
Preferred
Familiarity of sparse matrix storage representations.
Hands on experience with CNN, RNN, Transformer neural network architectures.
Experience with programming GPUs and specialized HW accelerator systems for deep neural networks.
Passionate about learning new compiler development methodologies like MLIR.
Enthusiastic about learning new concepts from compiler experts in the US and a willingness to defeat the time zone barriers to facilitate collaboration.
Benefits
d-Matrix is a computing platform that targets artificial intelligence inferencing workloads in the datacenter.