Senior System Software Engineer, Speech AI
NVIDIA · Posted Sep 30
Graphics processing units, artificial intelligence platforms, accelerated computing, and data center solutions
Get a personal compatibility score
Add a resume for personal matches
About the role
NVIDIA's Speech AI Engineering team builds GPU-accelerated AI systems and supports enterprise and developer customers deploying conversational AI. The team focuses on Automatic Speech Recognition (ASR), Text-to-Speech (TTS), Audio Language Models (ALM), and Speech-to-Speech (S2S) pipelines running at scale. This senior role involves hands-on customer engagement to implement, troubleshoot, and optimize speech systems in production, along with building and optimizing C++ and Python backend implementations and client SDKs.
What you will do
- Work on cutting-edge GPU-accelerated AI systems deployed at scale
- Tackle challenging problems in real-time streaming audio processing and low-latency inference
- Troubleshoot and resolve complex issues across ASR, TTS, ALM, and S2S pipelines
- Model Integration: Work alongside Model researchers to transition ASR, TTS and S2S models from research to production readiness.
- Develop Core Speech Services: Build and enhance C++ & python backend implementations for ASR, TTS, and S2S pipelines, leveraging CUDA for GPU acceleration
- Optimize Inference Performance: Improve streaming latency and throughput through advanced batching strategies, encoder caching, and multi-threaded pipeline optimizations
- Feature Development: Add new capabilities such as advanced voice activity detection, speaker diarization, decoder implementations (CTC, WFST, Flashlight), and text post-processing
- Client Libraries: Contribute to Python and C++ client SDKs and CLI tools for easy service integration
- Assist with API integration, SDK usage, model deployment, and performance optimization
- Provide advanced technical guidance to customers implementing speech technology solutions
Skills used in this role
What the employer is looking for
- Masters or BE/BTech in Computer Science, computer architecture, or related field
- 6+ years of experience
- Excellent C++ & Python programming and software design skills, including debugging, performance analysis, and test design.
- Experience with inference pipelines for LLM, Speech Recognition & Speech Synthesis
- Solid understanding of modern model architectures (Transformers, CNNs, RNNs)
- Excellent debugging abilities spanning multiple software (storage systems, kernels and containers)
- Experience building and deploying cloud services using HTTP REST, gRPC, Websockets and related technologies
- Strong collaborative and interpersonal skills, specifically a proven ability to effectively guide and influence within a dynamic matrix environment
- Ability to work independently, define project goals and scope and manage your own development effort.
- Knowledge of real-time streaming audio systems and low-latency architectures
- Experience with speech model fine-tuning or customization
Preferred qualifications
- Publications or contributions to ML optimization open-source projects.
- Experience with embedded systems or edge deployment
Benefits and support
- Compensation and benefits are detailed in the job posting
About NVIDIA
NVIDIA Corporation is a multinational technology company that designs graphics processing units (GPUs) for the gaming and professional markets, as well as system on a chip units (SoCs) for the mobile computing and automotive market. Pioneering accelerated computing, the company has become a driving engine of modern artificial intelligence, deep learning, and data center infrastructure.
- Industry
- Semiconductors
- Company size
- 42000+ employees
- Founded
- April 5, 1993
- Location
- Santa Clara, California, USA
- Funding stage
- Public Company
Funding
Public Company · $5M raised
Leadership
Founder, President and Chief Executive Officer
Executive Vice President and Chief Financial Officer
Founder and NVIDIA Fellow
Executive Vice President, Worldwide Field Operations
Recent coverage
NVIDIA Newsroom
NVIDIA Announces $1 Billion Commitment to Advance U.S. Super Intelligence Research and Quantum Leadership2026-10-08
NVIDIA Newsroom
NVIDIA Board of Directors Authorizes an Additional $150 Billion for Share Repurchases2026-10-03
NVIDIA Newsroom
NVIDIA Launches Open Agent Safety Platform to Secure Agents From Testing to Deployment2026-09-28
NVIDIA Newsroom
NVIDIA Reports Second Quarter Fiscal 2027 Financial Results with Record Revenue2026-08-26