Senior Machine Learning Applications and Compiler Engineer, LPX

Details

NVIDIA is seeking a senior engineer to develop algorithms and optimizations for its LPX inference and compiler stack. The role works at the intersection of large-scale systems, compilers, and deep learning, focusing on mapping neural network workloads onto future NVIDIA platforms.

Responsibilities

• Build, develop, and maintain high-performance runtime and compiler components, with a focus on end-to-end inference optimization.
• Define and implement mappings of large-scale inference workloads onto NVIDIA systems.
• Extend and integrate with NVIDIA's software ecosystem, including libraries, tooling, and interfaces for seamless model deployment across platforms.
• Benchmark, profile, and monitor performance and efficiency metrics to ensure efficient mappings of neural network graphs to inference hardware.
• Collaborate with hardware architects and design teams to provide software feedback, influence future architectures, and co-design features that improve performance and efficiency.
• Prototype and evaluate compilation and runtime techniques, including graph transformations, scheduling strategies, and memory/layout optimizations for spatial processors.
• Publish and present technical work on compilation approaches for inference and spatial accelerators at leading machine learning, compiler, and computer architecture venues.

Requirements

• MS or PhD in Computer Science, Electrical or Computer Engineering, or a related field, or equivalent experience, with 5 years of relevant experience.
• Strong software engineering background with proficiency in systems-level programming such as C/C++ and/or Rust.
• Solid computer science fundamentals, including data structures, algorithms, and concurrency.
• Hands-on experience with compiler or runtime development, including IR design, optimization passes, or code generation.
• Experience with LLVM and/or MLIR, including custom passes, dialects, or integrations.
• Familiarity with deep learning frameworks such as TensorFlow and PyTorch, and portable graph formats such as ONNX.
• Understanding of parallel and heterogeneous computing architectures, including GPUs, spatial accelerators, or other domain-specific processors.
• Strong analytical and debugging skills, including experience with profiling, tracing, and benchmarking tools.
• Excellent communication and collaboration skills across hardware, systems, and software teams.
• Experience with MLIR-based compilers or other multilevel IR stacks, particularly for graph-based deep learning workloads, is desirable.

Additional Qualifications

• Experience with spatial or dataflow architectures, static scheduling, pipeline parallelism, or tensor parallelism at scale.
• Contributions to open-source machine learning frameworks, compilers, or runtime systems, particularly in performance or scalability.
• Research impact demonstrated through publications or presentations at venues such as PLDI, CGO, ASPLOS, ISCA, MICRO, MLSys, or NeurIPS.
• Experience with large-scale distributed AI inference or training systems, performance modeling, and capacity planning for multi-rack deployments.

Compensation and Benefits

• Base salary for Level 3: USD 152,000–241,500 per year.
• Base salary for Level 4: USD 184,000–287,500 per year.
• Eligibility for equity and benefits.
• Applications will be accepted at least until July 17, 2026.
• This is an existing vacancy. NVIDIA uses AI tools in its recruiting processes and is an equal opportunity employer.