Software / ML Engineer
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.
Requirements:
- MS 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
- Experience with embedded systems and software SDK
- Startup mindset/experience
Experience in one or more of the following areas is 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
- Hands-on experience on developing compiler libraries or tools
- Hands-on experience with driver development for ASIC/FPGA