Remote | GPU Kernel Engineer — $60–$80/hour

We are sharing a specialised part-time consulting opportunity for experienced GPU and accelerator engineers with hands-on expertise in kernel development, numerical validation, performance optimisation, profiling, and low-level compute frameworks. This role focuses on evaluating GPU and accelerator kernel-development tasks for correctness, completeness, reproducibility, and performance quality. Selected engineers will review kernel implementations, benchmark methodology, compilation and runtime behaviour, numerical tolerances, and optimisation decisions across multiple accelerator ecosystems. Key Responsibilities GPU Kernel Development Review Evaluate GPU and accelerator kernels for technical correctness and completeness Review implementations developed from specifications or reference operators Assess whether kernels correctly implement intended mathematical behaviour Identify implementation defects, unsupported assumptions, or incomplete solutions Apply practical judgement grounded in hands-on kernel engineering experience CUDA & Accelerator Frameworks Review kernel development across frameworks such as CUDA, Triton, NKI, and Pallas (JAX) Assess framework-specific implementation choices and execution constraints Evaluate kernel translations or migrations between different frameworks Identify incorrect assumptions when moving implementations across accelerator ecosystems Compare alternative kernel implementations for correctness and technical quality Numerical Correctness Assess kernel outputs against suitable reference implementations Evaluate absolute, relative, and ULP-based tolerances Determine whether numerical differences fall within acceptable limits Review floating-point behaviour and precision-related edge cases Identify discrepancies caused by implementation defects rather than expected numerical variation Performance Profiling & Benchmarking Evaluate kernel performance using tools such as Nsight, Nsight Compute (ncu), roofline analysis, or framework-native profilers Assess whether benchmark methodology produces fair and meaningful comparisons Review latency, throughput, utilisation, and memory behaviour Identify misleading benchmarking practices or inappropriate baselines Determine whether claimed performance improvements are supported by evidence Kernel Performance Optimisation Review optimisation strategies for compute and memory efficiency Assess tiling, vectorisation, parallelisation, and workload decomposition Evaluate trade-offs between arithmetic throughput and memory movement Identify bottlenecks affecting kernel performance Assess whether optimisations preserve numerical correctness Memory Hierarchy Optimisation Review use of registers, shared memory, caches, and accelerator-specific memory resources Evaluate shared-memory tiling, register pressure, bank conflicts, and coalescing patterns Identify inefficient memory-access behaviour Assess data locality and memory-bandwidth utilisation Evaluate whether memory optimisations appropriately match the target hardware Compilation & Runtime Validation Diagnose common kernel compilation and runtime failures Review issues involving driver incompatibilities, out-of-memory conditions, launch configurations, shape or stride mismatches, and autotuning failures Determine whether failures originate from kernel logic, environment configuration, or runtime assumptions Evaluate proposed debugging approaches and corrective actions Assess whether tasks execute reliably in their intended environment Kernel Translation & Hardware Migration Review kernels translated or lowered across programming frameworks Evaluate migration between different accelerator targets Assess whether computational semantics and performance assumptions remain valid Identify platform-specific behaviour that requires redesign rather than direct translation Evaluate migration quality across GPU and custom-accelerator environments Debugging & Operator Fusion Review debugging tasks involving incorrect or unstable kernel implementations Diagnose failures using outputs, profiler data, runtime behaviour, and source code Evaluate operator-fusion strategies where relevant Assess whether fused kernels preserve intended semantics Identify optimisation decisions that introduce correctness or maintainability issues Compiler & Lowering Concepts Evaluate kernel tasks involving compiler or intermediate-representation concepts where applicable Review transformations between high-level operators and accelerator-level implementations Assess lowering decisions for correctness and efficiency Apply familiarity with MLIR or comparable compiler infrastructures where relevant Identify issues arising from compiler or code-generation assumptions Rubric-Based Technical Evaluation Assess assigned kernel tasks against structured technical criteria Provide clear written explanations supporting evaluation decisions Reference specific numerical, performance, compilation, or runtime evidence Apply evaluation standards consistently across assignments Distinguish valid implementation alternatives from technically flawed approaches Ideal Profile 3+ years of hands-on experience developing, optimising, or verifying GPU or accelerator kernels Practical experience with at least two of CUDA, Triton, NKI, or Pallas (JAX) Strong understanding of numerical correctness , including absolute, relative, and ULP tolerances Experience selecting and validating appropriate reference implementations Strong performance profiling and benchmarking experience Familiarity with Nsight, Nsight Compute, roofline analysis , or comparable profiling tools Strong understanding of common kernel compilation and runtime failure modes Experience with at least three of the following: Kernel generation from specification Framework translation or lowering Hardware-target migration Kernel debugging Performance optimisation Operator fusion Experience across both NVIDIA GPU and custom-accelerator ecosystems is preferred Background in compiler engineering, MLIR, or intermediate-representation lowering is advantageous Strong understanding of memory-hierarchy optimisation is preferred Contributions to kernel or accelerator libraries such as cuBLAS, cuDNN, Triton community kernels, or JAX/XLA custom calls are advantageous Strong written communication and ability to provide precise technical feedback Engagement Details Part-time independent contractor engagement Fully remote within the United States Flexible scheduling based on project requirements Compensation: $60–$80/hour Work focuses on GPU and accelerator kernel development, numerical correctness, performance optimisation, benchmarking, debugging, and technical quality evaluation Projects may be extended, shortened, or concluded based on project needs and performance Work must be completed without using confidential or proprietary information belonging to any employer, client, institution, or other third party H1-B and STEM OPT support is unavailable for this engagement About the Platform This opportunity is available through 24-MAG LLC. We connect experienced professionals with remote consulting opportunities across technical, evaluation, and project-based workstreams. By submitting this application, you acknowledge that your information may be processed by 24-MAG LLC for recruitment and opportunity matching in accordance with our Privacy Policy: https://www.24-mag.com/privacy-policy .