Senior Compiler Engineer, Agentic Compiler Systems

NVIDIA•Redmond, WA

About The Position

NVIDIA is seeking a Senior Compiler Engineer to build intelligent compiler technologies for its accelerated computing stack. The role works across compilers, agentic systems, numerical correctness, and verification to create systems that reason about, generate, optimize, and validate code transformations across software and hardware boundaries. The engineer will develop compiler-oriented agents and workflows, numerical validation and verification infrastructure, and collaborate with compiler, runtime, library, and hardware teams to deliver capabilities in production tools and products. The position includes designing intelligent low-level compiler systems and multi-step transformation workflows; developing systems that reason about low-level IR, code generation, optimization, scheduling, numerical precision, and GPU performance; building data, environments, verification, reward, and evaluation systems; and creating infrastructure for numerical validation, differential testing, regression detection, and correctness verification. The engineer will also co-design workflows across models and inference, compiler pipelines, runtimes, libraries, kernels, and GPUs, and drive performance analysis and optimization for correct, scalable, real-world deployment.

Requirements

Bachelor's degree in Computer Science, Electrical Engineering, Applied Mathematics, or a related field, or equivalent experience.
5+ years of relevant industry or academic experience in compilers, AI systems, numerical computing, verification, high-performance computing, or related areas.
Strong hands-on experience in compiler implementation, program analysis, code generation, optimization, low-level performance engineering, or correctness infrastructure.
Experience in at least one of agent systems, coding agents, compiler automation, numerical analysis, program verification, differential testing, or formal/semi-formal validation methods.
Strong C/C++ and Python programming skills, with solid software engineering fundamentals.
Experience with GPU programming and performance optimization using CUDA or comparable accelerator platforms.
Ability to work effectively across system boundaries, from model-driven workflows and compiler infrastructure to runtime and hardware-aware optimization.

Nice To Haves

MS or PhD degree.
Experience with Rust.
Track record of building high-impact compiler infrastructure, coding agents, verification frameworks, correctness tooling, or developer tools.
Deep expertise in low-level compiler stacks such as LLVM, MLIR, PTX, Triton, or other IR/codegen frameworks.
Experience building or optimizing AI-assisted compilation, numerical validation systems, equivalence checking, autotuning, or compiler verification workflows.
Deep expertise in GPU systems, numerical behavior, and performance optimization, demonstrated through benchmark results, deployed systems, publications, or widely used software.
Publications or open-source leadership in compilers, numerical computing, verification, formal methods, agentic AI, high-performance computing, AI systems, or programming systems.

Responsibilities

Design, build, and optimize intelligent low-level compiler systems, including compiler-oriented agents, multi-step transformation workflows, tool use, memory, and orchestration.
Develop systems that reason about low-level IR, code generation, optimization passes, scheduling, numerical precision, and performance tradeoffs across GPU-centric workloads.
Build data, environments, verification, reward, and evaluation systems to continuously improve compiler quality, numerical correctness, robustness, and performance.
Develop infrastructure for numerical validation, differential testing, regression detection, and correctness verification for generated or transformed code.
Co-design compiler and verification workflows across models and inference, compiler pipelines, runtimes, libraries, kernels, and GPUs.
Collaborate with internal compiler, CUDA, library, runtime, and hardware teams to integrate compiler, agentic, and verification capabilities into NVIDIA products.
Drive performance analysis and optimization for generated or transformed code, focusing on correctness, scalability, and real-world deployment.