Responsible for analyzing and optimizing deep learning (DL) and machine learning (ML) models, algorithms and applications on current and next generation Intel hardware and instruction sets.
Design, develop and optimize ML kernels and Algorithms for Deep Learning accelerators.
Profile distributed DL models to identify performance bottlenecks and propose solutions across individual component teams.
Interact with global implementation team and deep learning researchers in defining cutting edge solutions
Qualifications
Mtech/MS in CS, ECE or related fields
Hands-on experience with developing high performance, multi-threaded and distributed software on multi-core CPUs, compute clusters, GPUs and heterogeneous clusters is preferred.
Solid expertise in Distributed Algorithms and High Performance Computing algorithms
Experience in optimizing software systems for CPU/GPUs.
Strong statistics, applied math skills for real world HPC and Deep learning problems
Experience in any Machine learning/ Deep Learning Benchmarking process/tools is a plus.
Experience in Distributed Deep Learning is a big plus
Strong coding skills in C++ and Python is a MUST
Experience with compiler design and graph based optimizations is a plus
Good communication skills
Ability to work in a dynamic, cross-geo, startup-like environment
Job Detail
Industry :
IT-Software/Software Services
Job Function :
Engineering Design / R&D
Employment Type :
Full Time
Other Skills :
hr@itsws.com
Company Name :
Intel Technology India Pvt Ltd
Company Address :
23-56P, Devarabeesanahalli Varthur Hobli, Outer Ring Road Bangalore Bangalore KA 560103 IN