Job_Summary:
Nexa AI is an on-device AI research and deployment company specializing in tiny, multimodal models and local on-device inference frameworks. The Deep Learning Engineer (SDK) will focus on developing SDKs across multiple platforms and working with cloud technologies.
Responsibilities:
• Specialize in Google Cloud / AWS tech stacks
• Familiarity with LLM technologies, particularly with the Transformers library
• Experience with model compression is a plus
• Knowledge of model deployment on edge devices is a plus
• Contribute to the development of our SDKs across multiple platforms, including Android, iOS, and Linux
Qualifications:
-Required:
• Specialize in Google Cloud / AWS tech stacks
• Familiarity with LLM technologies, particularly with the Transformers library
• 2+ years of experience
• Minimum BS/MS in Computer Science
• Excellent CS fundamentals (data structures, algorithms, coding)
• Knowledge of OS internals, compilers, low-power/mobile optimization
• Experience with low-level code C and frameworks like CUDA, OpenCL
• Proficiency in multithreading and performance optimization
-Preferred:
• Experience with model compression is a plus
• Knowledge of model deployment on edge devices is a plus
Company:
Nexa AI (nexa.ai) is a Cupertino-based company specializing in on-device AI models and tools. Nexa AI has a track record of offering H1B sponsorships.