Optimize the inference performance of various DL models (CNN, NLP, etc.)

? Identify bottlenecks in performance and propose scalable solutions

? Finetune parameters and library-linked variables to extract the best output

? Benchmark & Low-level profiling to analyze hotspots

? Leverage hardware resources & distribute workload using parallel computing to obtain

optimal performance

Qualification:

? Bachelor of Engineering/Bachelor of Technology, Master of Engineering/Master of

Technology.

? Must have very good programming skills in Python

? Very sharp analytical & problem-solving skills

? Hands-on experience in working with any parallel workloads and multithreading

? Knowledge of Parallel Computing - CPU/GPU & Parallel Programming - OpenMP, CUDA

? Good knowledge of computer architecture & micro architectures like x86.

? Good to have knowledge of profiling tools like perf, gprof

? Nice to have DL framework knowledge (Tensorflow, Pytorch, ONNX) & exposure to DL

model architectures