Accelerator Compiler and Tool Chain Lead

Velaura AI, Inc.; Santa Clara (CA); Hybrid; USD 200,000 - 300,000; Full time

Job summary

Velaura AI, Inc. is seeking an Accelerator Compiler Lead to own the compiler and model-lowering stack for its AI accelerator.

You will drive the path from customer AI models to optimized executable artifacts for our NPU, including graph import, operator lowering, IR, graph transformations, quantization integration, and profiling. The ideal candidate has built or shipped compiler infrastructure for ML accelerators, GPUs, DSPs, or other heterogeneous compute targets.

Qualifications

• Proven experience in compiler development for ML accelerators.
• Strong knowledge of ML model formats, IRs, and quantization.
• Proficient in C++ and Python; production-grade software experience.

Responsibilities

• Lead architecture and development of the AI accelerator compiler stack.
• Own model ingestion and graph lowering from PyTorch export flows, ONNX, TensorFlow Lite.
• Define operator coverage strategy, lowering rules, graph transformations, fusion, partitioning, and fallback behavior.
• Develop compiler optimization passes for tensor layout, tiling, memory movement, mixed precision, operator fusion, and hardware-specific scheduling.
• Work closely with accelerator runtime and driver teams to define executable artifact formats, metadata, memory planning requirements, profiling hooks, and runtime constraints.
• Partner with hardware architecture and NPU firmware teams on ISA, command streams, tensor layouts, data movement, hardware constraints, and compiler-visible performance features.
• Own quantization compiler integration, including calibration metadata, precision selection, scale handling, layout constraints, and accuracy/performance tradeoffs.
• Build compiler diagnostics that help customers understand unsupported operators, shape constraints, graph rewrites, quantization issues, and performance bottlenecks.
• Establish compiler verification and regression strategy for graph transformations, IR lowering, numerical behavior, model accuracy, and performance.
• Hire, mentor, and lead a team of compiler and ML systems engineers.

Skills

Compiler development

ML graph compilers

Code generation

Accelerators

ML formats

Graph IRs

Operator lowering

Tensor layouts

Quantization

Runtime interfaces

C++

Python

Production-quality

Systems software

MLIR

LLVM

TVM

XLA

IREE

Glow

TensorRT

OpenVINO

Correctness risks

Graph rewrites

Mixed precision

Operator fusion

Lowering

Collaboration

Hardware architects

Firmware

Runtime engineers

Model integration

SQA

Team leadership

Architecture lead

Tools

MLIR

LLVM

TVM

XLA

IREE

Glow

TensorRT

OpenVINO

Job description

Role Overview

We are looking for an Accelerator Compiler Lead to own the compiler andmodel-lowering stack for Velaura’s AI accelerator.This role will lead the path fromcustomer AI models to optimized executable artifacts for our NPU, including graphimport, operator lowering, compiler IR, graph transformations, quantization integration,code generation, graph partitioning, and compiler diagnostics. The ideal candidate hasbuilt or shipped compiler infrastructure for ML accelerators, GPUs, DSPs, or otherheterogeneous compute targets.

Responsibilities

• Lead architecture and development of the AI accelerator compiler stack.
• Own model ingestion and graph lowering from frameworks and exchange formats such as PyTorch export flows, ONNX, TensorFlow Lite, or similar.
• Define operator coverage strategy, lowering rules, graph transformations, fusion, partitioning, and fallback behavior.
• Develop compiler optimization passes for tensor layout, tiling, memory movement, mixed precision, operator fusion, and hardware-specific scheduling.
• Work closely with accelerator runtime and driver teams to define executable artifact formats, metadata, memory planning requirements, profiling hooks, and runtime constraints.
• Partner with hardware architecture and NPU firmware teams on ISA, command streams, tensor layouts, data movement, hardware constraints, and compiler-visible performance features.
• Own quantization compiler integration, including calibration metadata, precision selection, scale handling, layout constraints, and accuracy/performance tradeoffs.
• Build compiler diagnostics that help customers understand unsupported operators, shape constraints, graph rewrites, quantization issues, and performance bottlenecks.
• Establish compiler verification and regression strategy for graph transformations,IR lowering, numerical behavior, model accuracy, and performance.
• Hire, mentor, and lead a team of compiler and ML systems engineers.

Required Qualifications

• Deep experience with compiler development, ML graph compilers, or code generation for accelerators, GPUs, DSPs, or heterogeneous compute systems.
• Strong understanding of ML model formats, graph IRs, operator lowering, tensorlayouts, quantization, and runtime/compiler interfaces.
• Strong C++ and Python programming skills and experience buildingproduction-quality compiler or systems software.
• Experience with compiler frameworks or technologies such as MLIR, LLVM,TVM, XLA, IREE, Glow, TensorRT-like systems, OpenVINO-like systems, orequivalent.
• Strong understanding of correctness risks in compiler optimizations, graph rewrites, mixed precision, operator fusion, and hardware-specific lowering.
• Ability to work closely with hardware architects, firmware engineers, runtime engineers, model-integration teams, and SQA.
• Experience leading technical teams or major architecture areas.

Preferred Qualifications

• Experience with NPU, GPU, DSP, or AI accelerator compiler stacks.
• Experience with quantization-aware compilation, mixed precision, sparsity, pruning, graph partitioning, or hardware-specific scheduling.
• Experience supporting ONNX, PyTorch export, TensorFlow Lite, JAX/XLA,TorchDynamo/TorchInductor, or other model import flows.
• Familiarity with robotics, computer vision, CNNs, transformers, detection,segmentation, depth, SLAM-adjacent perception, or edge AI workloads.
• Experience building customer-facing compiler diagnostics and model-portingtools.
• Experience with model-zoo release processes, accuracy validation, and reproducible benchmark artifacts.
• Open-source compiler contributions or experience working with externalframework communities.

$200,000 - $300,000 a year

Compensation & Benefits

At Velaura, we believe exceptional talent deserves exceptional rewards. Compensation for this role includes a base salary and very competitive equity compensation, allowing team members to share in the company’s long-term success.

The base pay listed represents a good faith estimate that the Company reasonably expects to pay for this position at the time of hire. Actual compensation will depend on multiple factors, including the candidate's skills, qualifications, relevant experience, and geographic location.

In addition to base salary and equity compensation, Velaura offers a comprehensive benefits package that may include medical, dental, and vision coverage; paid time off; flexible work arrangements; professional development opportunities; and other benefits designed to support the well-being and growth of our team.

Velaura is committed to pay equity and transparency and regularly benchmarks compensation to ensure we remain competitive in the market.

Why Velaura?

Velaura is building next-generation compute technology for cloud, edge, and PhysicalAI. Our solutions will enable robots, autonomous systems, drones, and other intelligentmachines to operate efficiently in the physical world.
This is an opportunity to help build foundational technology at a time when the industry is undergoing fundamental change. You will work alongside experienced leaders, architects, engineers, and operators who have delivered industry-defining products across mobile, cloud, semiconductor, and AI platforms. If you enjoy solving difficult problems, working across disciplines, and helping shape thefuture of Physical AI, we would love to hear from you.

Equal Employment Opportunity and Accommodations

Velaura is an Equal Opportunity Employer that is committed to inclusion and diversity.Qualified applicants will receive consideration for employment without regard to race,color, religion, national origin, gender, sexual orientation, gender identity, disability orprotected veteran status. We also take affirmative action to offer employment
opportunities to minorities, women, individuals with disabilities, and protected veterans.

Velaura is committed to working with qualified individuals with physical or mentaldisabilities. Applicants who would like to contact us regarding the accessibility of ourwebsite or who need special assistance or a reasonable accommodation for any part ofthe application or hiring process may contact us at: [e-mail]. This contact
information is for accommodation requests only. Evaluation of requests for reasonableaccommodation will be determined on a case-by-case basis.