Computer Vision Model Developer (Deployment Engineer)

Job Title: Senior Computer Vision Model Developer (Deployment Engineer)

Location: Nearshore – flexible on the work hours for their time zones

Duration: 6 months + extension (likely 12 months)

Start: ASAP after budget approval at end of month

As a  Senior AI Deployment Engineer, you will work with a team of AI scientists, AI and xR application engineers, software engineers and clinical experts to design, develop, and deploy computer vision, augmented reality, mixed reality, multi-modal AI models and GenAI features into existing and new medical device products. This is a unique, high visibility opportunity for talented individuals who want to dive deep into cutting-edge AI model optimization for mobile edge deployments.

Technical Responsibilities

Develop and deploy Artificial Intelligence (AI) powered software on mobile edge devices (iPhone, iPad, Vision Pro, Android systems)

Optimize AI models and pipelines for real-time inference on mobile edge devices

Debug memory constraints, threading, and concurrency issues

Design deployment evaluation frameworks, develop unit tests for software components in compliance with regulatory requirements

Generate and review the necessary documents with project teams

Perform Software verification and validation testing

Perform code reviews as an independent reviewer following best coding standards and practices

Minimum Qualification

Bachelor's degree in software engineering / computer science or related discipline with 4+ years of relevant work experience OR Master’ in a relevant discipline and 2+ years of experience OR PhD degree in a relevant discipline. ​​​​

Preferred Qualifications

• 4+ years of Python development experience.

• ​ 3+ years of experience developing and deploying AI models on iOS and/or Android platform

• ​ 2+ years of iOS development experience (Xcode, Swift)

• ​ Android mobile development experience is a plus

• ​ Familiarity with mobile AI architectures (Apple Neural Engine, Metal Performance Shaders, Qualcomm DSP / GPU)

• ​ Experience converting models from PyTorch to CoreML / TensorFlow Lite / ONNX Runtime Mobile, performing custom model optimization etc.

• ​ Experience integrating AI models into native mobile applications (Swift, Objective-C, Kotlin, Java)

• ​ Experience troubleshooting unsupported ops and custom layers during model conversion

• ​ Experience with CI/CD Git automation pipelines

• ​ Proven ability to optimize AI models for real-time inference on edge devices to meet latency and performance requirements

• ​ Knowledge of model optimization techniques (quantization, pruning, graph optimization, distillation, etc.)

• Experience with VisionOS development is a big plus ​​