Staff Deep Learning Compiler Engineer

We Love AI Jobs; Burlingame, Northern (CA, KY); Híbrido; USD 170 000 - 230 000; Tempo integral

Resumo da oferta

Quadric is seeking a Staff Deep Learning Compiler Engineer in Burlingame, CA to build and optimize the compiler stack that maps neural network frameworks to Quadric’s edge processor. You will work on graph transformations, code generation, and performance profiling in close collaboration with hardware teams.

The role requires 8+ years in deep learning compiler development, strong C++ and Python skills, and experience with MLIR, TVM, LLVM, PyTorch, TensorFlow, and ONNX.

Qualificações

• 8+ years hands-on experience developing deep learning compilers or compiler infrastructures.

Responsabilidades

• Design, implement, and maintain compiler optimization passes targeting Quadric’s processor architecture using MLIR, TVM, or LLVM.
• Develop lowering pathways from high-level ML frameworks (PyTorch, TensorFlow, ONNX) to optimized low-level kernel code.
• Optimize neural network performance for memory throughput, latency, compute unit utilization, and power consumption.
• Implement graph-level optimizations, including operator fusion, layout transformation, quantization, and memory allocation strategies.
• Analyze novel model topologies and extend compiler support for new operators and primitives.
• Benchmark and profile end-to-end model performance to identify and resolve bottlenecks.
• Collaborate with hardware teams to define instruction set extensions and compiler requirements.
• Develop software simulators and test benches to validate compiler correctness and performance.
• Participate in hardware bring-up and validation on FPGA/ASIC platforms.

Conhecimentos

C++

Python

MLIR

Apache TVM

LLVM

PyTorch

TensorFlow

ONNX

Formação académica

BS, MS, or PhD in CS/CE/EE

Ferramentas

MLIR

Apache TVM

LLVM

PyTorch

TensorFlow

ONNX

Descrição da oferta de emprego

# Staff Deep Learning Compiler EngineerQuadricBurlingame, CA (HQ)Full-time$170,000 – $230,000 / yearAI tools:MLIRApache TVMLLVMPyTorchTensorFlowONNXXLATensorRTUpload your resume once and Scout applies for youApply with ScoutShare this job:LinkedInXSave imageThis staff engineer will build and optimize the deep-learning compiler stack that maps neural network frameworks to Quadric’s edge processor. The role spans graph transformations, code generation, performance profiling, and collaboration with hardware teams on co-design and validation.* Permanent* On-site* 8+ years* BS, MS, or PhD### Skills and expertiseC++PythonMLIRApache TVMLLVMPyTorchTensorFlowONNX### Key responsibilities* Develop compiler optimization passes and lowering pathways for Quadric’s processor architecture.* Implement graph transformations, including operator fusion, quantization, and memory allocation strategies.* Profile model performance and collaborate with hardware teams on compiler and architecture requirements.## How this job comparesCompared with 94 open staff machine learning jobs on October 10, 2026.Pay: This job pays $170K to $230K a year. The 56 open staff machine learning jobs that publish US pay start at $219K on average, so this job starts about 22% lower.Similar open jobs: We Love AI Jobs lists 94 open staff machine learning jobs at 53 companies.Remote work: This job is on site. 16 of the 94 staff machine learning jobs (17%) are remote.AI in this role: High. AI is the core of the work: building, training or deploying AI systems. The role builds the compiler stack used to run neural networks on Quadric hardware. It directly handles model graphs, operators, quantization, and end-to-end AI performance.## Full descriptionQuadric is redefining edge AI with the industry's first General Purpose Neural Processing Unit (GPNPU), enabling developers to run both neural network inference and conventional C++ code on a single programmable architecture. Our technology powers intelligent edge devices across automotive, industrial, robotics, and embedded systems.Founded in 2016 and based in downtown Burlingame, California, Quadric is building the world's first supercomputer designed for the real-time needs of edge devices. Quadric aims to empower developers in every industry with superpowers to create tomorrow's technology, today. The company was co-founded by technologists from MIT and Carnegie Mellon, who were previously the technical co-founders of the Bitcoin computing company 21.The OpportunityQuadric is building the world’s first General-Purpose Neural Processing Unit (GPNPU) architecture, bringing high-performance AI, DSP, and ML compute to edge devices. As a Deep Learning Compiler Engineer, you will design and optimize the compiler stack (MLIR, TVM, LLVM) that bridges state-of-the-art neural network frameworks directly to our proprietary hardware architecture. You'll play a critical role in unlocking peak hardware performance, low latency, and memory efficiency for edge AI workloads.What You'll DoDeep Learning Compiler Infrastructure & Optimization• Design, implement, and maintain compiler optimization passes targeting Quadric’s processor architecture using frameworks like MLIR, Apache TVM, or LLVM.• Develop lowering pathways from high-level machine learning frameworks (PyTorch, TensorFlow, ONNX) down to optimized low-level kernel code.• Optimize neural network performance for memory throughput, latency, compute unit utilization, and power consumption.Neural Network Model Parsing & Graph Transformation• Implement graph-level optimizations, including operator fusion, layout transformation, quantization (INT8/FP16), and memory allocation strategies.• Analyze novel deep learning model topologies (Transformers, CNNs, Vision-Language Models) and extend compiler support for new operators and primitives.• Benchmark and profile end-to-end model performance to identify and resolve compiler bottlenecks.Hardware-Software Co-Design• Collaborate closely with hardware and micro-architecture teams to define instruction set extensions, hardware acceleration features, and compiler requirements.• Develop software simulators, functional models, and test benches to validate compiler correctness and generated binary performance.• Participate in hardware bring-up and validation efforts on FPGA and ASIC platforms.What Success Looks LikeWithin your first 6–12 months, you'll:• Successfully integrate support for key deep learning models (e.g., modern Transformer architectures or Vision models) into Quadric's compiler pipeline.• Implement custom graph and codegen optimization passes that deliver measurable performance improvements on target benchmarks.• Partner with the architecture team to influence the next-generation micro-architecture definition through data-driven workload analysis.What We're Looking ForRequired• BS, MS, or Ph.D. in Computer Science, Computer Engineering, Electrical Engineering, or a related field.• 8+ years Hands-on experience developing deep learning compilers or compiler infrastructures (e.g., MLIR, Apache TVM, LLVM, XLA, TensorRT, or Glow).• Strong proficiency in C++ (14/17/20) and Python, with solid fundamentals in data structures, algorithms, and object-oriented design.• Familiarity with modern AI/ML frameworks (PyTorch, TensorFlow, ONNX) and deep learning operator representations.• Solid understanding of computer systems, memory hierarchies, parallel processing, and CPU/GPU/NPU instruction execution.