Principal AI Compiler – Runtime Engineer

Jobtailor; Palo Alto (CA); On-site; USD 180,000 - 250,000; Full time

Job summary

Jobtailor, based in Palo Alto, seeks a senior engineer to build and optimize compiler and runtime infrastructure for modern AI workloads. The role focuses on efficient execution across GPUs/TPUs/NPUs and hardware accelerators, applying AI techniques to software optimization and co-design.

The candidate will collaborate with inference, systems, and hardware teams, profiling and benchmarking to remove bottlenecks and drive state-of-the-art AI infrastructure. International travel may be required.

Qualifications

• BSc, MSc, or PhD in Computer Science, Engineering, Mathematics, or a related discipline
• Strong programming skills in C/C++ and/or Python in Linux environments using common development tools
• Solid understanding of machine learning fundamentals and modern AI workloads
• Experience applying AI technologies to software engineering, performance optimization, and hardware-aware design challenges
• Experience with AI compiler frameworks and infrastructure such as Mojo/Max, MLIR, LLVM, XLA, OpenXLA, Triton, or Gluon
• Knowledge of compiler optimizations including operator fusion, graph transformations, scheduling, code generation, and lowering pipelines
• Experience with AI runtimes and execution frameworks such as ONNX Runtime, TensorRT, TVM Runtime, IREE Runtime, or XLA
• Experience optimizing machine learning workloads on GPUs, TPUs, NPUs, DSPs, or custom accelerators
• Experience with hardware-aware software development and AI accelerator enablement
• Experience developing high-performance kernels and operators such as GEMMs, convolutions, attention, normalization, or quantization
• Experience with distributed AI training or inference systems
• Experience with model execution frameworks such as Max, PyTorch, TensorFlow, JAX, or ONNX
• Ability to travel periodically; international travel may be required
• Nice-to-have experience with Modular (Mojo/Max), OpenXLA, StableHLO, Torch-MLIR, Triton, TVM, or IREE
• Nice-to-have contributions to open-source projects such as LLVM, MLIR, PyTorch, OpenXLA, Triton, Gluon, or xDSL

Responsibilities

• Build and optimize compiler and runtime infrastructure for modern AI workloads
• Enable efficient execution of machine learning models across GPUs, NPUs, TPUs, and custom AI accelerators
• Apply modern AI technologies and methodologies to improve software development, system optimization, and software-hardware co-design processes
• Collaborate with inference, systems, and hardware teams to improve software-hardware co-design
• Investigate and resolve performance bottlenecks through profiling, benchmarking, and system-level analysis
• Contribute to state-of-the-art AI infrastructure and optimize software for emerging AI hardware
• Help define how modern machine learning workloads are represented, compiled, and executed at scale
• Travel periodically for collaboration with global teams and stakeholders

Skills

C/C++ Programming

Python Programming

AI Compiler Frameworks

Machine Learning Optimization

Performance Profiling

Education

BSc/MSc/PhD in CS/Engineering/Math

Tools

Mojo/Max

MLIR

LLVM

XLA

ONNX Runtime

TensorRT

Triton

Gluon

PyTorch

TensorFlow

Job description

• Build and optimize compiler and runtime infrastructure for modern AI workloads
• Enable efficient execution of machine learning models across GPUs, NPUs, TPUs, and custom AI accelerators
• Apply modern AI technologies and methodologies to improve software development, system optimization, and software-hardware co-design processes
• Collaborate with inference, systems, and hardware teams to improve software-hardware co-design
• Investigate and resolve performance bottlenecks through profiling, benchmarking, and system-level analysis
• Contribute to state-of-the-art AI infrastructure and optimize software for emerging AI hardware
• Help define how modern machine learning workloads are represented, compiled, and executed at scale
• Travel periodically for collaboration with global teams and stakeholders

Requirements

• BSc, MSc, or PhD in Computer Science, Engineering, Mathematics, or a related discipline
• Strong programming skills in C/C++ and/or Python in Linux environments using common development tools
• Solid understanding of machine learning fundamentals and modern AI workloads
• Experience applying AI technologies to software engineering, performance optimization, and hardware-aware design challenges
• Experience with AI compiler frameworks and infrastructure such as Mojo/Max, MLIR, LLVM, XLA, OpenXLA, Triton, or Gluon
• Knowledge of compiler optimizations including operator fusion, graph transformations, scheduling, code generation, and lowering pipelines
• Experience with AI runtimes and execution frameworks such as ONNX Runtime, TensorRT, TVM Runtime, IREE Runtime, or XLA
• Experience optimizing machine learning workloads on GPUs, TPUs, NPUs, DSPs, or custom accelerators
• Experience with hardware-aware software development and AI accelerator enablement
• Experience developing high-performance kernels and operators such as GEMMs, convolutions, attention, normalization, or quantization
• Experience with distributed AI training or inference systems
• Experience with model execution frameworks such as Max, PyTorch, TensorFlow, JAX, or ONNX
• Ability to travel periodically; international travel may be required
• Nice-to-have experience with Modular (Mojo/Max), OpenXLA, StableHLO, Torch-MLIR, Triton, TVM, or IREE
• Nice-to-have contributions to open-source projects such as LLVM, MLIR, PyTorch, OpenXLA, Triton, Gluon, or xDSL

Core Competencies

Demonstrates expertise in building and optimizing compiler and runtime infrastructure for AI workloads, with strong programming skills in C/C++ and Python. Proficient in applying AI technologies to enhance software development and performance optimization across various hardware platforms.

Highest-signal resume keywords

• C/C++ Programming
• Python Programming
• AI Compiler Frameworks
• Machine Learning Optimization
• Performance Profiling

Hard Skills

• Compiler Optimization
• Machine Learning Fundamentals
• High-Performance Kernels
• Distributed AI Training
• Software-Hardware Co-Design

Industry Keywords

• AI Workloads
• Custom AI Accelerators
• Performance Bottlenecks
• Graph Transformations
• AI Runtimes

Tools & Technologies

• LLVM
• MLIR
• ONNX Runtime
• TensorRT
• PyTorch