Senior DL Performance Efficiency Architect

What you'll do

• Lead cross-layer efforts to improve LLM efficiency across model architecture, training systems, and inference.
• Analyze how LLM workloads map to GPUs, memory systems, interconnects, and distributed infrastructure.
• Identify and execute opportunities for model-system-hardware co-design.
• Establish a measurement-driven roadmap for LLM efficiency from initial investigation to production deployment.
• Influence future roadmaps for models, software, and hardware by partnering with cross-functional engineering teams.
• Perform performance analysis, roofline modeling, and workload characterization to identify fundamental bottlenecks.
• Implement optimizations for low-precision computation, quantization, sparsity, and speculative decoding.

What we're looking for

• MS or PhD degree in Computer Science, Electrical Engineering, Computer Engineering, or a related field.
• 5+ years of relevant experience in AI systems, model architecture, computer architecture, high-performance computing, or performance optimization.
• Strong understanding of LLM architectures and the trade-offs between model quality, cost, memory footprint, latency, throughput, and power.
• Strong background in performance analysis, roofline modeling, workload characterization, benchmarking, and hardware-aware optimization.
• Proven ability to provide technical leadership and drive complex optimization projects from concept to production.
• Experience with low-precision computation, quantization, sparsity, Mixture-of-Experts, long-context inference, and speculative decoding.
• Experience co-designing model architectures with training, inference, compiler, or hardware constraints.
• Experience influencing accelerator, system, or datacenter architecture based on future AI workload requirements.