Senior ML Engineer @ Intuitive Surgical
Art Jiang
Building high-performance imaging pipelines for safety-critical medical systems. Expert in real-time 4K video processing and depth estimation on edge devices.
Technical Skills
ML inference, GPU acceleration, and real-time imaging systems
ML Inference
PyTorchTensorRTONNX RuntimeQuantizationMemory OptimizationNsight Systems/Compute
GPU & HPC
CUDADLA OffloadingNsight ProfilingcuDNNTensor Cores
Languages
PythonC/C++CUDA
Image Processing
OpenCVStereo DepthCamera CalibrationDe-BayerHDRLow-Light Enhancement
Computer Vision
Object DetectionSegmentationMonoscopic Depth EstimationSuper-ResolutionPose Estimation
Platforms
Jetson Orin/Xavier/Thor AGXHoloscan SDKJetPack
Infrastructure
BazelDockerJenkinsAzure/AWSAirflowKafka
Work Experience
Selected roles in ML, computer vision, and medical devices
Senior Machine Learning Engineer
Intuitive Surgical
Sunnyvale, CA
- GPU-accelerated video pipeline on NVIDIA Orin AGX achieving ultra low end-to-end latency for 4K stereo surgical endoscopy with real-time depth estimation
- CUDA Kernel development & TensorRT optimization achieving 1.8x throughput improvement
- Offline privacy-centric, voice-enabled VLLM RAG system for real time usage on edge device
- Trained video world foundation models for surgical simulation with multimodal controls
- Led development of iMED multi-endoscope dataset for sub-pixel reprojection accuracy
- Built real-time auto-focus system using eye-tracking with Holoscan SDK, processing 120fps video streams
Machine Learning Engineer
Intuitive Surgical
Sunnyvale, CA
- Developed 4K stereo surgical endoscope prototype with NVIDIA Jetson Orin, integrated with Da Vinci 5 & Xi
- Led SurgiSR4K dataset development for super-resolution research (MICCAI 2025)
- Developed next-gen camera sensor bring-up and ISP with downstream pattern recognition
- Developed Image Stacking pipeline for surgical applications
- Yocto OS and BSP development
Machine Learning Intern
Intuitive Surgical
Sunnyvale, CA
- Implemented BiLSTM and AutoEncoder NLP models for automated error log classification
- Reduced RMA with predictive failure modeling
Software Engineer
Fresenius, NA R&D
- Developed Class-2 life-critical medical software for hemodialyzer used by millions of patients
- Built cloud-based telehealth infrastructure with Apache Airflow, dbt, Databricks, and Snowflake
- QNX RTOS OS development
Featured Work
Recent projects and research
Intuitive Surgical
GPU-Accelerated Video Pipeline
Ultra-low latency 4K stereo surgical endoscopy with real-time depth estimation on NVIDIA IGX.
NVIDIA & JHU Research
SurgVerse: Video World Foundation Models
Diffusion-based architectures for surgical simulation with multimodal camera trajectory generation.
Let's Connect
Interested in collaboration or have questions about my work? Connect with me on LinkedIn.
Connect on LinkedIn