AI Infrastructure Engineer
About The Position
The AI Infrastructure Engineer designs, builds, and maintains the scalable, high-performance infrastructure that enables AI models for medical imaging to transition from research into validated, production-ready clinical systems. This role focuses on supporting multi-modal data pipelines (multispectral imaging, RGB color imaging, structured clinical metadata), GPU-accelerated model deployment and inference, and robust, compliant inference pipelines used in clinical and operational environments. The engineer serves as a critical bridge across AI research, data science, software engineering, and regulated deployment.
Requirements
- Master's or PhD in Computer Science, Engineering, or related field
- Minimum of 1 year of industry experience supporting production-level AI/ML systems, infrastructure, or deployment pipelines
- Proficient in Python and C++
- Experience with cloud platforms (AWS, GCP, or Azure)
- Experience with model serving and inference frameworks (TensorRT, ONNX Runtime)
- Hands-on experience with containerization (Docker, Kubernetes) and CI/CD pipelines
- Familiarity with ML frameworks like PyTorch or TensorFlow from a systems perspective
- Knowledge of CUDA programming and GPU optimization
Nice To Haves
- Deep understanding of neural network architectures and training methodologies
- Experience in productizing medical image algorithms on GPU platforms
- Publications in top-tier conferences (CVPR, ICCV, ECCV, NeurIPS, ICML)
Responsibilities
- Architect and maintain scalable infrastructure for medical imaging AI workflows, including MSI/RGB data ingestion, preprocessing, training, evaluation, and deployment
- Build reliable model serving pipelines that integrate with clinical software systems
- Improve image chain & algorithm performance compared to initial benchmarks
- Optimize CUDA kernels for maximum GPU utilization and performance
- Support acceleration strategies for workflow-constrained clinical use cases
- Work closely with Data Scientists, Computer Vision Engineers, and Software Engineers to operationalize AI models
- Partner with clinical, QA, and regulatory teams to ensure infrastructure supports validated and auditable AI workflows
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Mid Level
Number of Employees
51-100 employees
