Senior ML Inference & Compiler Engineer

Segment (Twilio); Santa Clara (CA); On-site; USD 152,000 - 287,500; Full time

Job summary

NVIDIA is seeking a Senior Machine Learning Applications and Compiler Engineer to develop high-performance runtime and compiler components for LPX inference and compiler stack. You will map large-scale inference workloads onto NVIDIA platforms and extend with libraries, tooling, and interfaces for seamless model deployment across ecosystems.

You will collaborate with hardware teams, prototype new compilation techniques, and publish results at top venues.

Qualifications

• MS or PhD in Computer Science, Electrical/Computer Engineering, or related field (or equivalent experience) with 5+ years in the domain.
• Strong software engineering background with systems-level programming (C/C++ and/or Rust) and solid CS fundamentals.
• Hands-on experience with compiler or runtime development, including IR design, optimization passes, or code generation.

Responsibilities

• Build and maintain high-performance runtime and compiler components for end-to-end inference optimization.
• Define mappings of large-scale inference workloads onto NVIDIA systems.
• Extend with NVIDIA SW ecosystem, contributing libraries, tooling, interfaces for models across platforms.
• Benchmark and profile performance, ensuring efficient mappings of graphs to inference hardware.
• Collaborate with hardware architects to feedback software observations for future architectures.

Skills

C/C++

Rust

LLVM/MLIR

Data structures & algorithms

Parallel architectures

Education

MS or PhD in CS/EE or related field

Tools

LLVM

MLIR

ONNX

TensorFlow

PyTorch

Job description

NVIDIA is seeking a Senior Machine Learning Applications and Compiler Engineer to develop high-performance runtime and compiler components for LPX inference and compiler stack. You will map large-scale inference workloads onto NVIDIA platforms and extend with libraries, tooling, and interfaces for seamless model deployment across ecosystems.

You will collaborate with hardware teams, prototype new compilation techniques, and publish results at top venues.