Nvidia Senior DL Algorithms Engineer - Inference Optimizations 

United States, Texas 

634788816

What you will be doing:

• Deliver hyper-optimized recipes for LLM inference as part of NVIDIA Inference Microservices (NIMs).

• Analyze, validate and debug performance and accuracy characteristics of optimized models.

• Benchmark state-of-the-art offerings in LLM inference and perform competitive analysis for NVIDIA SW/HW stack.

• Develop software, tooling and processes across multiple layers of the stack to streamline and scale the delivery of hundreds of optimized LLM models.

• Collaborate heavily with other SW/HW co-design teams to enable the creation of the next generation of AI-powered services.

What we want to see:

• PhD in CS, EE or CSEE or equivalent experience.

• 5+ years of experience.

• Experience with delivering results under tight timelines and rapidly changing requirements.

• Strong background in deep learning and neural networks, in particular inference.

• Deep understanding of computer architecture, and familiarity with the fundamentals of GPU architecture.

• Programming skills in C++ and Python.

Ways to stand out from the crowd:

• Strong fundamentals in algorithms.

• Experience and good understanding of LLMs and/or VLMs.

• Proven experience with processor and system-level performance modelling.

• Experience with MLOps and DLOps, building CI/CD pipelines

• GPU programming experience (CUDA or OpenCL) is a strong plus but not required.