Nvidia System Software Engineer Speech AI 

India, Karnataka, Bengaluru 

143019270

What you’ll be doing:

• Develop conversational AI software to serve predictions from trained neural networks running on GPUs for Speech Synthesis(TTS)

• Develop GPU accelerated implementations of sophisticated speech AI algorithms like Speech Synthesis(TTS), Voice style transfer, Neural G2P, Neural Network based Vocoders

• Analyzing performance bottlenecks and implementing optimization techniques

• Collaborate with various teams on new product features and improvements of existing products

What we need to see:

• Masters or Bachelors (or equivalent experience) in Computer Science, computer architecture, or related field

• 3+ years of experience

• Excellent C++ programming and software design skills, including debugging, performance analysis, and test design

• Experience with inference Services for Speech Recognition, speech synthesis, Speech Translation, Machine Translation

• Background with productization of TTS models( FastPitch, Tacotron etc.) & vocoders(HifiGan)

• Experience with Multithreading, IPC, Distributed systems programming

• Excellent Debugging abilities spanning multiple software (storage systems, kernels and containers)

• Experience building and deploying cloud services using HTTP REST, gRPC, protobuf, JSON and related technologies

• Familiarity with version control and code review tools like Git, Gerrit.

Ways to stand out from the crowd:

• Background with container technologies such as docker

• Experience with Helm charts for deployment of containers & managing kubernetes applications

• Python Programming

• Knowledge of GPU programming such as OpenCL or CUDA