Senior System Software Engineer, Speech AI

NVIDIA Gruppe; Pune District; On-site; INR 1,500,000 - 2,500,000; Full time

Job summary

NVIDIA Gruppe is seeking an experienced Software Engineer in Pune District, India to work on their GPU-accelerated Speech AI platform. You will be responsible for building and optimizing core services for speech recognition and text-to-speech applications.

The ideal candidate should have a Masters in Computer Science and over 4 years of experience with C++ and Python. You will improve performance and contribute to service integration with modern technologies. NVIDIA values diversity and is an equal opportunity employer.

Qualifications

• 4+ years of experience in software engineering.
• Deep knowledge of multi-threading and synchronization.
• Experience with inference pipelines for Speech Recognition & Synthesis.

Responsibilities

• Develop C++ & Python backend implementations for speech services.
• Improve performance and optimize inference pipelines.
• Contribute to Python and C++ client SDKs.

Skills

C++ programming

Python programming

Performance analysis

Debugging skills

Multi-threading knowledge

Education

Masters or BE/BTech in Computer Science

Tools

Bazel

Job description

We're seeking an experienced Software Engineer to work on NVIDIA’s high-performance GPU-accelerated Speech AI platform. You'll contribute to building and optimizing core speech recognition (ASR), text-to-speech (TTS), and S2S services that power real-time conversational AI applications at scale. If you're creative ∓ passionate about solving real world conversational AI problems, come join our Speech AI Engineering team.

What you’ll be doing:

• 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
• Performance Analysis: Profile and debug complex multi-threaded systems, identifying bottlenecks in GPU/CPU pipelines

What we need to see:

• Masters or BE/BTech in Computer Science, computer architecture, or related field
• 4+ 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
• Systems Programming: Deep knowledge of multi-threading, synchronization primitives, thread pools, and concurrent data structures
• Build Systems: Hands‑on experience with Bazel or similar build systems
• Performance Optimization: Track record of identifying and resolving performance bottlenecks in latency‑sensitive systems
• Experience building and deploying cloud services using HTTP REST, gRPC, Websockets and related technologies

Ways to stand out from the crowd:

• Publications or contributions to ML optimization open‑source projects.
• Experience with embedded systems or edge deployment

NVIDIA is committed to fostering a diverse work environment and proud to be an equal opportunity employer. As we highly value diversity in our current and future employees, we do not discriminate (including in our hiring and promotion practices) on the basis of race, religion, color, national origin, gender, gender expression, sexual orientation, age, marital status, veteran status, disability status or any other characteristic protected by law.