Senior Software Engineer, Quantized Inference

Invidia

Multiple Locations
Base: 152,000 usd - 241,500 usd (level 3), 184,000...
Python programming proficiency
Familiarity with c++
Experience with ml accelerators
NVIDIA is seeking software engineers to accelerate the discovery and deployment of efficient inference recipes for LLMs to unlock throughput and latency gains without regressing accuracy

Job Summary

  • NVIDIA is seeking software engineers to accelerate the discovery and deployment of efficient inference recipes for LLMs to unlock throughput and latency gains without regressing accuracy.
  • The role involves implementing quantized and sparse recipes in inference engines, owning model export pipelines, and building prototypes and benchmarking tools to evaluate performance.
  • Employees will be eligible for equity and benefits, with a base salary range depending on level and location, and will work in a diverse and inclusive environment committed to equal opportunity.

Matching Summary

NVIDIA is seeking software engineers to accelerate the discovery and deployment of efficient inference recipes for LLMs to 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 proficiency
  • Familiarity with C++
  • Experience with ML accelerators
  • PyTorch internals knowledge
  • Software engineering fundamentals
  • Quantized inference implementation
  • Kernel development experience

Nice-to-have

  • Experience with inference serving frameworks
  • Triton kernel development
  • Debugging numerical issues
  • Model compression techniques
  • Collaboration with partner teams
  • Building benchmarking harnesses
  • Developing data analysis tooling

Key Requirements

  • MS/PhD in Computer Science or related field or equivalent experience
  • 4+ years relevant software engineering experience
  • Strong written and verbal communication skills
  • Ability to work with ambiguous requirements

Work Rights

Not specified

Tailored Resume

Cover Letter