Software Engineer, AI Engineer (Applied​/Software), Machine Learning​/ ML Engineer

Company Description

United Imaging Intelligence (UII), founded in 2017, is a global medical artificial intelligence company with offices in Shanghai and Boston. The company develops AI solutions that power intelligent medical equipment, advance biomedical research, and optimize clinical workflows from screening and diagnosis to treatment and follow-up. UII has built more than 10 AI platforms and over 100 AI applications, now deployed in over 3,000 hospitals worldwide.

Its strong focus on clinical quality is demonstrated by multiple regulatory approvals, including FDA‑cleared, CE‑marked, and Class III NMPA‑certified products. Candidates joining UII will contribute to impactful healthcare innovations in a rapidly growing, international environment.

We are seeking a Software Engineer with strong computer vision and robotics experience to join our AI engineering team in Burlington, MA. In this role, you will design, build, and deploy vision‑based perception systems that run on real hardware — from camera integration and sensor calibration to optimized AI inference on embedded platforms such as NVIDIA Jetson. You will work closely with AI researchers, hardware engineers, and clinical collaborators to bring state‑of‑the‑art perception algorithms from prototype to product.

• Design, implement, and maintain computer vision and perception software in C++ and Python for real‑time applications
• Integrate and calibrate camera systems (RGB, depth, stereo) and work directly with embedded hardware platforms such as NVIDIA Jetson
• Optimize deep learning models for deployment using TensorRT, including quantization, layer fusion, and latency/throughput profiling
• Collaborate with AI research teams to productize vision models for detection, segmentation, tracking, and 3D understanding
• Develop robust, well‑tested, and maintainable software using strong data structures and algorithmic foundations
• Build and maintain CI/CD pipelines and containerized deployments using Git Lab and Docker
• Debug and profile full‑stack vision pipelines across hardware, drivers, middleware, and application layers
• Contribute to system architecture decisions, code reviews, and engineering best practices

• Bachelor's or Master's degree in Computer Science, Electrical Engineering, Robotics, or a related field
• Proficiency in C++ and Python
  , with experience writing production‑quality, performance‑critical code
• Hands‑on experience working with hardware — cameras (industrial, depth, stereo) and embedded platforms such as NVIDIA Jetson
• Solid understanding of AI/deep learning methodologies and their practical applications in computer vision
• Experience with TensorRT for model optimization and deployment (ONNX export, FP16/INT8 quantization, inference profiling)
• Strong data structures and algorithms skills, with the ability to reason about performance and memory
• Experience with modern development workflows:
  Git Lab (version control, CI/CD),
  Docker
  , and Linux environments

• Experience with robotics frameworks (ROS/ROS2), motion control, or sensor fusion
• Familiarity with camera calibration, multi‑view geometry, SLAM, or 3D reconstruction
• Experience deploying AI models in regulated or safety‑critical environments (medical devices a plus)
• Knowledge of CUDA programming and GPU performance optimization
• Familiarity with deep learning frameworks (PyTorch, Tensor Flow) and model conversion pipelines
• Experience with real‑time video processing pipelines (GStreamer, Deep Stream)