C++ Inference Engineer
Core
Designing and optimizing low-latency C++ inference pipelines for real-time AI systems in a surgical platform, handling data from cameras and sensors under strict regulatory constraints.
Role type
Senior C++ Inference Engineer (Real-Time Systems)
Builds
Production-ready, low-latency AI inference frameworks for live surgical environments
Domain
Medical technology / Robotics / Computer Vision
Deliverable
production ML models
Required skills
Modern C++ (C++17/20+), Real-time system design, Multithreading and concurrency, Performance optimization (CPU/GPU), AI inference pipeline development, Regulated environment experience (FDA/IEC 62304)
Preferred skills
CUDA, Hardware integration, Medical imaging systems
Technologies
C++, CUDA, GPU
Responsibilities
Building real-time, multithreaded C++ pipelines for AI inference, Optimizing latency and memory usage across CPU and GPU, Working with imaging pipelines and sensor data, Developing production systems within FDA-regulated environments
Seniority
Senior, hands-on IC
