Machine Learning Engineer, OpenGradient

• Bachelor's or Master's degree in Computer Science, Engineering, Mathematics, or a related field
• Strong background in machine learning, deep learning, and statistical modeling with hands-on experience in developing and deploying ML infrastructure
• Proficiency in programming languages such as Python, Java, C++, Go
• Extensive experience with popular ML frameworks (e.g., TensorFlow, PyTorch, HuggingFace) and technologies (e.g. CUDA, ONNX)
• Experience as a software engineer with deep understanding of algorithms and data structures
• Have familiarity with the latest AI and ML research and working knowledge of how these systems are efficiently implemented

Desirable

• We are seeking a self-driven and motivated Machine Learning Engineer with a specialized focus on building robust infrastructure tailored for handling large-scale inference workloads for AI and ML models
• You will spearhead the design, development, and optimization of high-performance AI/ML systems capable of supporting real-time and batch processing requirements across diverse domains
• You will collaborate closely with cross-functional teams to architect and implement cutting-edge inference pipelines and infrastructure, ensuring the reliability, efficiency, and scalability of our machine learning model deployments
• Design and implement scalable and efficient machine learning inference infrastructure and architecture to support real-time and batch processing requirements
• Develop deployment pipelines and tools for deploying machine learning models into production environments, including containerization (e.g., Docker) and orchestration (e.g., Kubernetes)
• Optimize model inference performance and resource utilization through techniques such as model quantization, pruning, and acceleration (e.g., GPU/TPU utilization, model caching)
• Continuously evaluate and improve the performance of machine learning models and infrastructure through experimentation and optimization techniques