Nexa AI is an on-device AI research and deployment company. We specialize in tiny, multimodal models (e.g. Octopus v2, OmniVLM, OmniAudio), local on-device inference framework (e.g. nexa-sdk), and model optimization techniques (e.g. NexaQuant). Our work has been recognized by industry leaders like Google, Hugging Face, AMD, and more. And we partner with enterprises and SMBs to bring local intelligence to every device.
Responsibilities
Builds on device ML infrastructure at scale
Assist in developing and optimizing LLMs for on-device deployment
Support on-device AI research efforts
Contribute to the development of our SDKs across multiple platforms, including Windows, MacOS, Android, iOS, and Linux
You May Be a Good Fit If You
Minimum BS/MS in Computer Science
Familiar with PyTorch
Excellent understanding of computer science fundamentals, including data structures, algorithms, and coding
Knowledge of operating system internals, compilers, and low-power/mobile optimization
Experience with low-level programming in C and frameworks like CUDA, OpenCL
Proficiency in multithreading and performance optimization