diff --git a/.buildkite/pipeline.yml b/.buildkite/pipeline.yml
index e20ce5dd9c7..f3e0a6a6ce7 100644
--- a/.buildkite/pipeline.yml
+++ b/.buildkite/pipeline.yml
@@ -885,13 +885,13 @@ steps:
       - label: "GPU: GPU dry baroclinic wave - 4 gpus"
         key: "target_gpu_implicit_baroclinic_wave_4process"
         command:
-            nsys profile --delay 100 --trace=nvtx,cuda,mpi --output=target_gpu_implicit_baroclinic_wave_4process/output_active/report-%q{PMI_RANK}
           - mkdir -p target_gpu_implicit_baroclinic_wave_4process
           - >
             srun --cpu-bind=threads --cpus-per-task=4
             julia --threads=3 --color=yes --project=examples examples/hybrid/driver.jl
             --config_file ${GPU_CONFIG_PATH}/target_gpu_implicit_baroclinic_wave.yml
             --job_id target_gpu_implicit_baroclinic_wave_4process
+          - nsys profile --delay 100 --trace=nvtx,cuda,mpi --output=target_gpu_implicit_baroclinic_wave_4process/output_active/report-%q{PMI_RANK}
         artifact_paths: "target_gpu_implicit_baroclinic_wave_4process/output_active/*"
         env:
           CLIMACOMMS_CONTEXT: "MPI"