Senior Machine Learning Engineer, Quantized Inference

Invidia

Multiple Locations
Base: 152,000 usd - 241,500 usd (level 3), 184,000...
Python programming
Pytorch framework
Quantization and sparsity techniques
NVIDIA is seeking machine learning engineers to accelerate the discovery and deployment of efficient inference recipes for LLMs that unlock throughput and latency gains without regressing accuracy

Job Summary

  • NVIDIA is seeking machine learning engineers to accelerate the discovery and deployment of efficient inference recipes for LLMs that unlock throughput and latency gains without regressing accuracy.
  • The candidate will prototype state-of-the-art quantization and sparsity recipes, design and execute rigorous experiments, and collaborate with inference framework and post-training teams to ensure scalable model serving.
  • The role offers a competitive salary range, equity, benefits, and the opportunity to contribute to open-source projects and publish findings at ML conferences.

Matching Summary

NVIDIA is seeking machine learning engineers to accelerate the discovery and deployment of efficient inference recipes for LLMs that unlock throughput and latency gains without regressing accuracy.

Salary

Base: 152,000 USD - 241,500 USD (Level 3), 184,000 USD - 287,500 USD (Level 4); Bonus/Equity: Eligible for equity; Benefits: Eligible for benefits

Skills & Requirements

Must-have

  • Python programming
  • PyTorch framework
  • Quantization and sparsity techniques
  • LLM evaluation methodology
  • Experiment design and execution
  • Numerical debugging in ML workloads

Nice-to-have

  • Post-training quantization experience
  • Quantization-aware training
  • SFT and RLHF/DPO pipelines
  • Inference serving frameworks familiarity
  • Open-source contributions
  • ML conference publishing

Key Requirements

  • MS/PhD in Computer Science or related field
  • 3+ years applied ML experience
  • Strong written and verbal communication
  • Ability to work with ambiguous requirements

Work Rights

Not specified

Tailored Resume

Cover Letter