Overview
In this role you bridge ML research and production, building robust SDKs and automating deployment for computer vision workloads across edge devices to cloud GPUs. You will port and optimize models for diverse hardware, ensuring efficient, high-throughput performance. You collaborate with cross-functional teams to deliver scalable solutions that enable real-time vision capabilities. This is an opportunity to shape how Zebra brings vision-powered capabilities to customers and partners at scale.
Pay / Benefits
- incentive-based annual cash bonus target 12% of base pay
Responsibilities
- SDK development (C++) to expose CV capabilities
- Port, convert, and deploy ML models across Qualcomm SoCs, Intel CPUs, and NVIDIA GPUs
- Optimize performance with hardware-specific toolkits
- Conduct evaluation and benchmarking on target hardware
- Build automation scripts and CI/CD pipelines using Python
Key requirements
- C++14/17/20 with STL, memory management, and multi-threading
- Python for automation and data processing
- Experience with at least one of: SNPE/QNN (Qualcomm), OpenVino (Intel), TensorRT (NVIDIA), TensorFlow Lite
- Familiarity with Docker for consistent environments
- Bachelor’s or Master’s in Computer Science or related field
- Bonus: Deep Learning fundamentals (CNNs, Transformers, Object Detection); model conversion and quantization (PTQ, QAT)
- C++14/17/20
- STL
- memory management
- multithreading
- Python
- SNPE/QNN (Qualcomm)
…
