Senior System Software Engineer, Speech AI
Salary not listed • India, Pune • Full-time
Posted 1mo ago
Remote Work Policy
On-site
Employment Type
Full-time
Categories
LLM Engineer
About the job
NVIDIA is seeking a Senior System Software Engineer with deep expertise in speech technologies to support enterprise and developer customers. This role involves hands-on technical engagement with customers to implement, troubleshoot, and optimize Automatic Speech Recognition (ASR), Text-to-Speech (TTS), Audio Language Models (ALM), and Speech-to-Speech (S2S) systems in production environments. If you're creative and passionate about solving real-world conversational AI problems, join our Speech AI Engineering team at the forefront of technological advancement.
Responsibilities
- 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.
- Collaborate with Model researchers to transition ASR, TTS, and S2S models from research to production readiness.
- Build and enhance C++ and Python backend implementations for ASR, TTS, and S2S pipelines, leveraging CUDA for GPU acceleration.
- Optimize inference performance through advanced batching strategies, encoder caching, and multi-threaded pipeline optimizations.
- Develop new capabilities such as advanced voice activity detection, speaker diarization, decoder implementations (CTC, WFST, Flashlight), and text post-processing.
- 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.
Requirements
- Master's or BE/BTech in Computer Science, computer architecture, or related field.
- 6+ years of experience.
- Excellent C++ and Python programming and software design skills, including debugging, performance analysis, and test design.
- Experience with inference pipelines for LLM, Speech Recognition, and Speech Synthesis.
- Solid understanding of modern model architectures (Transformers, CNNs, RNNs).
- Excellent debugging abilities spanning multiple software layers (storage systems, kernels, containers).
- Experience building and deploying cloud services using HTTP REST, gRPC, Websockets, and related technologies.
- Strong collaborative and interpersonal skills, with the ability to effectively guide and influence within a dynamic matrix environment.
- Ability to work independently, define project goals and scope, and manage development efforts.
- Knowledge of real-time streaming audio systems and low-latency architectures.
- Experience with speech model fine-tuning or customization.