ML Model Software Engineer/Compiler/ML Software Engineer

Company: TetraMem - Accelerate The World
Location: Fremont
Posted on: August 2, 2022

Job Description:

TetraMem is a fast-growing well-funded startup company working on the next generation of computing platforms with unique ReRAM-based in-memory computing technologies. We are hiring in multiple positions from software to hardware.
In this role you will be part of a world-class system design team responsible for the development and deployment of software solutions for a revolutionary computing system, which we believe can reduce the energy consumption of AI processing by two orders of magnitude over conventional digital solutions. This will completely disrupt the AI IoT landscape. It is based on our unique computing memory device with multi-bit-level capacity per cell, which is nonvolatile with excellent retention and endurance. We offer a very competitive compensation, commensurate with experience, and a full benefits package including medical, professional PTO, 401k, daycare subsidy, and other perks.
Compiler/ML Software EngineerRequirements:--- MS or PhD in Computer Engineering/CS/EE--- 5+ years commercial HW engineering experience--- Experience developing compilers for GPU compiler, dataflow compiler, or ML compiler--- Experience with ML model quantization and pruning techniques--- Startup mindset/experience
Experience in one or more of the following areas considered a strong plus:--- Knowledge of popular CPU/GPU compilers such as GCC, Clang--- Knowledge of ML compilers such as Glow, TVM, MLIR, or XLA--- Experience with LLVM and other open-source compiler libraries and tools--- Publications on compilation of ML or dataflow programs for HW acceleration

ML Model Software Engineer In this role you will be part of a world-class system design team responsible for the development and deployment of software solutions for a revolutionary computing system, which we believe can reduce the energy consumption of AI processing by two orders of magnitude over conventional digital solutions. This will completely disrupt the AI IoT landscape. It is based on our unique computing memory device with multi-bit-level capacity per cell, which is nonvolatile with excellent retention and endurance. We offer a very competitive compensation, commensurate with experience, and a full benefits package including medical, professional PTO, 401k, daycare subsidy, and other perks.
Requirements:--- MS or PhD with published research work in ML model optimization, post-training quantization, consideration of different datasets and different constrains (bit-accuracy, model size, latency and so on).--- Experience with popular ML frameworks, such as PyTorch and TensorFlow--- Startup mindset/experience
Experience in one or more of the following areas considered a strong plus:--- Experience with popular light-weight ML models on edge inference--- Hands-on experiences with deploying/evaluating ML models on resource/power-limited computing platforms.--- Experience providing technical leadership and/or guidance to other engineers

Keywords: TetraMem - Accelerate The World, Fremont , ML Model Software Engineer/Compiler/ML Software Engineer, IT / Software / Systems , Fremont, California