Building high-performance AI inference systems, distributed LLM serving infrastructure, and GPU-optimized real-time pipelines.

• 🔥 Focused on low-latency AI inference and GPU optimization
• 🚀 Experienced with TensorRT-LLM, CUDA, vLLM, ONNX Runtime
• 🧠 Interested in distributed AI systems and runtime performance engineering
• 📈 Passionate about quantization, CUDA Graphs, and scalable AI infrastructure
• 🎓 MS in Robotics & Autonomous Systems @ Arizona State University

Inference & GPU Optimization
TensorRT • TensorRT-LLM • CUDA • CUDA Graphs • ONNX Runtime • vLLM

Machine Learning
PyTorch • Transformers • FP16 • BF16 • FP8 • INT8 Quantization

Systems & Infrastructure
Docker • Linux • Async Execution • Multi-threading

Profiling & Performance
Nsight Systems • Nsight Compute • PyTorch Profiler • CUDA Events

• High-throughput LLM serving
• CUDA kernel optimization
• Low-latency inference systems
• Distributed AI infrastructure
• GPU runtime performance engineering