Senior AI Systems Performance Engineer

Responsibilities

• Bring up and optimize cutting-edge foundation models (e.g., DeepSeek, Llama, Qwen) on the SambaNova platform
• Profile and enhance model performance across compiler, runtime, and hardware layers
• Collaborate with machine learning, compiler, runtime, and hardware teams on co-designed AI applications
• Integrate advances in model architecture, quantization, scheduling, and memory optimization
• Develop robust, scalable, and efficient end-to-end inference solutions
• Identify performance bottlenecks and propose optimizations for single-node and distributed systems

Requirements

• Bachelor's or higher degree in Computer Science, Electrical Engineering, or related field
• 3+ years of experience in deep learning optimization, compiler/runtime optimization, or software-hardware co-design
• Proficiency in Python or C++
• Strong foundations in algorithms, data structures, and numerical computing
• Experience with PyTorch, TensorFlow, or JAX
• Demonstrated ability to analyze and optimize performance in real-world ML pipelines

Preferred Qualifications

• Hands-on experience with LLM or multimodal model training and inference
• Background in large-scale distributed training and high-throughput inference systems
• Familiarity with quantization, graph optimization, kernel fusion, and model partitioning
• Experience with DeepSpeed, Megatron, vLLM, or TensorRT
• Strong GPU programming skills (CUDA, Triton, or OpenCL)
• Knowledge of memory hierarchy optimization and scheduling

About the Company

SambaNova Suite™ is a full-stack, generative AI platform, from chip to model, optimized for enterprise and government organizations. Powered by the intelligent SN40L chip, it provides an integrated platform for secure and accurate generative AI deployment.