About this role
This full-time role in Hyderabad, India focuses on deploying and optimizing deep learning models for specialized ML accelerator hardware. The posting describes the role as Software Engineer (2–3 years experience), while the job-detail title is Senior Software Engineer Modelzoo.
Responsibilities
- Port and deploy models from frameworks such as PyTorch and TensorFlow to proprietary or commercial ML accelerators.
- Improve inference latency and throughput on target hardware. Contribute to quantization, including INT8, to reduce model size and accelerate inference while maintaining accuracy.
- Profile and debug the inference pipeline to identify and resolve performance bottlenecks.
Required qualifications
- Proficiency in PyTorch or TensorFlow, strong C++ and Python skills, and hands-on experience deploying and optimizing models on GPUs or other specialized accelerators.
- Some experience with post-training quantization; familiarity with inference engines and runtimes such as TensorRT, OpenVINO, and TensorFlow Lite; a foundational understanding of computer architecture; and proficiency with Git and collaborative development workflows.
- A bachelor’s or master’s degree in Computer Science, Electrical Engineering, or a related field.
Additional and preferred qualifications:
- Experience with GPU programming models such as CUDA or cuDNN is a plus.
- Preferred qualifications include hardware-aware model design, deep learning compiler technologies, real-time or embedded systems, cloud platforms such as AWS, GCP, or Azure, and CI/CD pipelines for ML models.
Skills for this role
PyTorchTensorFlowDeep learningModel deploymentModel quantizationPost-training quantizationINT8ML inferencePerformance profilingGPU accelerationC++PythonTensorRTOpenVINOTensorFlow LiteComputer architectureGitCUDAcuDNNHardware-aware model designDeep learning compilersEmbedded systemsReal-time systemsAWSGCPAzureCI/CD