Deep Learning Model Optimization Engineer

About the Role

is hiring Deep Learning Model Optimization Engineers to build, train, and optimize state-of-the-art deep learning models for high-performance production deployment. This role sits at the intersection of research and systems engineering, with a strong focus on inference efficiency across GPUs and edge devices.

Key Responsibilities

• Design and implement deep learning models (CNNs, Transformers, hybrid architectures).
• Build scalable training pipelines and distributed training workflows.
• Apply model compression techniques: quantization, pruning, and knowledge distillation.
• Optimize inference using TensorRT, ONNX Runtime, OpenVINO, or TVM.
• Profile and analyze performance bottlenecks using GPU profiling tools.
• Develop custom CUDA/C++ kernels when required.
• Benchmark latency, throughput, and accuracy across hardware platforms.
• Collaborate on deployment using Triton Inference Server and c...