Senior Research Engineer - Enterprise Products - Remote

Overview

We are looking for a Senior Research Engineer passionate about Generative AI inference, dedicated to developing optimized inferencing technologies to support growing generative AI needs.

In Short

• Develop new models and algorithms focused on Large Language Models.
• Design and implement multi-node serving architectures.
• Optimize multi-LoRA inference serving systems.
• Apply sophisticated quantization techniques to reduce model footprint.
• Implement latency optimization strategies.
• Demonstrate good engineering practices and mentor team members.
• Collaborate with engineering teams across NVIDIA.
• Strong communication and interpersonal skills required.
• A history of mentoring junior engineers is a plus.
• Passion for software engineering and continuous learning.

Requirements

• 8+ years of industry experience in Deep Learning frameworks.
• Excellent C++ and Python development skills.
• Understanding of modern techniques in Machine Learning.
• Strong computer science fundamentals.
• Desire to grow and learn new technologies.
• Experience in architecting large-scale distributed systems is a plus.
• Knowledge of CPU and/or GPU architecture.
• GPU programming (CUDA) experience is beneficial.

Benefits

• Base salary determined by location and experience.
• Salary range: 184,000 USD - 299,000 USD for Level 4.
• Salary range: 224,000 USD - 356,500 USD for Level 5.
• Eligible for equity and benefits.
• Commitment to diversity and equal opportunity.