Senior Applied Research Engineer - Accelerator Programming Model and Compiler

Job Title

Senior Applied Research Engineer - Accelerator Programming Model and Compiler

Role Summary

Work on the programming model, SDK, and LLVM-based compiler backend for NVIDIA's Programmable Vision Accelerator (PVA), a VLIW/SIMD accelerator used across DRIVE, Jetson, and IGX platforms. The role spans research and production systems software: defining public APIs and runtimes, improving code generation, and integrating the toolchain with AI coding agents.

Experience Level

Senior — typically requires 10+ years of relevant experience in low-level systems, compilers, or accelerator software.

Responsibilities

Key responsibilities include research, design, and implementation across programming models, compiler backends, runtimes, and agent integration.

• Design and implement the PVA programming model, SDK, and runtime APIs.
• Develop and improve an LLVM-based VPU compiler backend targeting a VLIW/SIMD architecture.
• Define benchmarks and evaluate AI-generated and developer-written PVA code for correctness and performance.
• Abstract hardware details into declarative interfaces usable by AI agents and developers.
• Integrate PVA workloads into CUDA-based heterogeneous pipelines (execution, memory movement, synchronization).
• Improve compile-time, emulator performance, and diagnostic tooling to aid development and agent workflows.
• Collaborate with internal and external customers to drive adoption and refine runtime APIs for real-world workloads.

Requirements

Must-have technical skills and experience for immediate contribution. Nice-to-have items indicate advantage but are not required.

• 10+ years building high-performance, low-level systems software, accelerator software, embedded software, or compiler/toolchain infrastructure.
• Proven experience designing higher-level programming abstractions, DSLs, or compiler IRs that preserve performance while hiding hardware complexity.
• Experience with compiler, debugger, linker, or toolchain development, particularly using LLVM.
• Experience developing code with AI coding agents and integrating compilers/tools with agentic development harnesses.
• Experience programming SIMD/VLIW processors and low-level performance engineering.
• Strong C++ development skills, low-level debugging, and performance profiling experience.
• Experience with Linux or QNX development environments.
• Strong communication and collaboration skills.
• Nice to have: CUDA integration experience, OpenCL, MLIR, Halide, TVM, Triton, graph compilers, image-processing DSLs, or other compiler-based systems.
• Nice to have: familiarity with ISO 26262, IEC 61508, or equivalent safety/quality standards; experience building agent harnesses and orchestrating multi-agent workflows.

Education Requirements

BS, MS, or PhD in Computer Science, Computer Engineering, Electrical Engineering, or a related technical field, or equivalent practical experience.

About the Company

Company: NVIDIA

Headquarters: Santa Clara, California, USA

NVIDIA is a global leader in accelerated computing, renowned for its innovative solutions in AI and digital twins that transform diverse industries. The company specializes in networking technologies, providing end-to-end InfiniBand and Ethernet solutions for servers and storage that optimize performance and scalability. NVIDIA serves sectors such as high-performance computing, enterprise data centers, and cloud computing, constantly reinventing its products and services to stay ahead in the market.