Nvidia Senior Research Engineer - Enterprise Products 

United States, Texas 

923062221

What you will be doing:

• Developing new models and algorithms focused on Large Language Models, Natural Language Processing, and Deep Learning.

• Design and implement multi-node serving architectures disaggregated serving and distributed LLM inference

• Optimize multi-LoRA (and other PEFT technique) inference serving systems

• Apply sophisticated quantization techniques (FP4/INT4, FP8) to reduce model footprint while preserving quality

• Implement speculative decoding (draft target, eagle, medusa etc) and other latency optimization strategies

• Demonstrating good engineering practices and mentoring other team members to do the same.

• Collaborating with engineering teams across all of NVIDIA to ensure our software integrates seamlessly up and down the NVIDIA accelerated serving stack.

What we need to see:

• Understanding of modern techniques in Machine Learning, Deep Neural Networks, Natural Language Processing, or Speech Recognition.

• 8+ years of industry experience in Deep Learning frameworks (PyTorch or TensorFlow).

• Passion for software engineering, especially with excellent C++ and Python development skills, with meaningful contributions to major open-source projects.

• Strong communication and interpersonal skills, along with the ability to work in a dynamic and distributed team. A history of mentoring junior engineers and interns is a huge plus.

• Bachelor's degree or equivalent experience.

• A desire to constantly grow and learn new things.

• Strong computer science fundamentals - algorithms and data structures, computational complexity, parallel and distributed computing, system software.

Ways to stand out from a crowd:

• Experience architecting or developing large-scale distributed systems for deep learning.

• Knowledge of CPU and/or GPU architecture.

• GPU programming (CUDA).