ChainOpera AI is the world’s first truly decentralized and open AI platform for simple, scalable, and trustworthy collaborative AI economy, and the AI app ecosystem for accessible and democratized AI - our GPUs, our model, our personal AI.

ChainOpera AI is supported by

• Enterprise-level generative AI platform for system scalability, model performance, and security/privacy (ChainOpera AI Platform)

• Leading open source library in large-scale distributed training, model serving, and federated learning (FedML)

• Innovative and unique edge-cloud collaborative AI models and systems towards on-device personal AI (Fox LLM)

• Internet veterans for serving billion-level end users based on cloud computing and mobile internet

• Established researchers in blockchain, machine learning, and large-scale distributed systems (80000+ citations)

• Ecosystem partnership with GPU providers, model developers, AI platforms, and AI applications

• Top-tier investors, angels, and advisors

Responsibilities:

• Develop novel algorithms and architectures for distributed and decentralized inference of large-scale AI models

• Design and implement techniques to optimize inference speed, reduce latency, and improve resource utilization in decentralized environments

• Collaborate with blockchain experts to integrate AI inference protocols with distributed ledger technologies

• Conduct cutting-edge research at the intersection of AI, distributed systems, and blockchain technology, with a focus on inference optimization

• Publish research findings in top-tier conferences and journals

• Work closely with engineering teams to transition research prototypes into production-ready inference systems

• Stay current with the latest advancements in AI, particularly in the areas of model compression, quantization, and efficient inference techniques

Requirements:

• Ph.D. in Computer Science, Machine Learning, or a related field

• Strong background in machine learning, deep learning, and distributed systems, with a focus on model inference

• Experience with large-scale model deployment and optimization techniques

• Proficiency in Python and deep learning frameworks (e.g., PyTorch, TensorFlow)

• Familiarity with distributed computing frameworks and edge computing technologies

• Excellent problem-solving skills and ability to think creatively about inference optimization

• Strong publication record in top-tier AI conferences or journals, particularly in the area of efficient model inference

Preferred Qualifications:

• Experience with blockchain technologies and decentralized systems

• Knowledge of model compression techniques, quantization, and hardware-aware neural architecture search

• Familiarity with edge AI and IoT deployments

• Track record of open-source contributions to AI or distributed systems projects related to model inference

• Experience mentoring junior researchers or leading research projects in the field of efficient AI inference