Nvidia Test Floor Engineer 

Taiwan, Taiwan Province, Hsinchu 

875321009

What you’ll be doing:

• Architect, implement and optimize reliable low latency full duplex conversation pipelines and dialog systems, that excel across various application areas and challenging environments.

• Build and benchmark cascaded and unified speech-to-speech models and systems that reflect real human conversations.

• Designing, implementing and testing domain specific agents and workflows and a framework which can support multi-turn, multi-modal, multi-user conversations with LLM driven agents.

• Analyze RAG and conversational AI agent end to end accuracy and limitations and recommend the next course of action & Improvements.

• Characterize performance and quality metrics across platforms for various AI and system components

• Collaborate with various teams on new product features and improvements of existing products. Customize and integrate the conversational AI framework with other NVIDIA products

• Participate in developing and reviewing code, design documents, use case reviews, and test plan reviews and help innovate, identify problems, recommend solutions and perform triage in a collaborative team environment.

What we need to see:

• Bachelor's degree or Master’s degree (or equivalent experience) in Computer Science, Electrical Engineering, Artificial Intelligence, or Applied Math

• 10+ years of experience, with a very good hands-on exposure to building solutions that touch various technology areas that cover Speech, LLM, RAG and Agents.

• Excellent programming skills in Python and/or C++, with ability to debug complex asynchronous systems

• Deep understanding of various Speech technologies like VAD, ASR, TTS, Translation, End-to-End Speech Models, etc. to build conversation systems.

• Experience working with RAG and LLM based applications as a key part of building Dialog and Q & A systems. Additional exposure to LLM function calling, Information Retrieval, Vector Databases, Embedding and Rerank models, autonomous agents etc.is welcome.

• Understanding of scalable deployment of multiple microservices involving Speech components, LLM driven RAG and Agent applications in production environment

• Experience working with protocol and transports like HTTP REST, gRPC, Websockets, WebRTC, etc.

• Hands on experience with building microservices and client-server applications.

• Familiarity with Docker, helm, kubernetes etc.

• Experience of working on end to end Software lifecycle, release packaging & CI/CD pipeline

• General background around version control and code review tools like Git, Gerrit, Gitlab.

Ways to stand out from the crowd:

• Strong fundamentals in Programming, Optimizations and Software design

• Experience of working with open source frameworks like LangChain, LlamaIndex for building LLM driven applications

• Strong knowledge of ML/DL techniques, algorithms and tools with exposure to Speech and Language Models

• Familiarity with GPU based technologies like CUDA, CuDNN and TensorRT

• Background with deploying machine learning models on data center, cloud, and embedded systems