Deep Learning Compiler Engineer
quadric.io, Inc
Burlingame, california
Job Details
Full-time
4/16/2024
Full Job Description
Quadric has created an innovative general purpose neural processing unit (GPNPU) architecture. Quadric's co-optimized software and hardware is targeted to run neural network (NN) inference workloads in a wide variety of edge and endpoint devices, ranging from battery operated smart-sensor systems to high-performance automotive or autonomous vehicle systems. Unlike other NPUs or neural network accelerators in the industry today that can only accelerate a portion of a machine learning graph, the Quadric GPNPU executes both NN graph code and conventional C++ DSP and control code.
If making an impact and having a seat at the table is important to you, this is the opportunity for you. Join our small, rapidly-growing team at Quadric to develop supercomputer technology designed for the Edge. In this position, you will be a core member of our team, and will have an opportunity to grow in the company of expert technologists who also happen to be good people you’ll want to spend time with.
What We Value:
Integrity, Humility, Happiness
What We Expect:
Initiative, Collaboration, Completion
Role:
As a senior member of our platform software engineering team, you will be tasked with lowering and optimizing neural networks on the quadric EPU. You will design and implement algorithmic optimizations to extract maximum performance out of the Quadric architecture.
Responsibilities:
- Drive the lowering and optimization of cutting edge deep neural networks using Quadric’s technology
- Apply your skills and expertise in mathematical & algorithmic optimization toward solving NP-hard problems
- Collaborate within the software team to develop algorithms that optimize graph-based execution on the Quadric architecture
Requirements
- MS or Ph.D. in Computer Science, or related field, with a minimum of eight years of experience in the industry
- Strong background in numerical and/or algorithmic optimization
- Understanding of building application-appropriate heuristics for NP-hard problems
- Knowledge of both classical as well as ML algorithms, e.g., Computer Vision, DSP, DNNs, etc.
- Strong background in graphs and related algorithms
Nice to haves:
- Proficiency in C++ >= 11
- Experience using / developing in TVM
- Knowledge of front-end and back-end compiler techniques
Expected Outcomes in 12 months:
- Develop a deep understanding of the hardware platform and low level software and leverage that for optimal performance of applications.
- Have a proven track record of implementing optimization passes for efficient lowering of deep learning and high performance computing algorithms on the Quadric EPU parallel processor.
Benefits
- Provide competitive salaries and meaningful equity
- Provide a politics free community for the brilliant minds who want to make an immediate impact
- Provide an opportunity for you to build long term career relationships
- Foster an environment that allows for lasting personal relationships alongside professional one
Founded in 2016 and based in downtown Burlingame, California, Quadric is building the world’s first supercomputer designed for the real-time needs of edge devices. Quadric aims to empower developers in every industry with superpowers to create tomorrow’s technology, today. The company was co-founded by technologists from MIT and Carnegie Mellon, who were previously the technical co-founders of the Bitcoin computing company 21.
Quadric is proud to be an equal opportunity workplace and is an affirmative action employer. We are committed to equal employment opportunity regardless of race, religion, sex, national origin, sexual orientation, age, citizenship, marital status, or disability.