diff --git a/noxfile.py b/noxfile.py
index 2e7154fd4e..936cf8b29b 100644
--- a/noxfile.py
+++ b/noxfile.py
@@ -255,7 +255,7 @@ def system(session):
     if system_test_folder_exists:
         session.run(
             "py.test",
-            "--quiet",
+            "-v",
             f"--junitxml=system_{session.python}_sponge_log.xml",
             system_test_folder_path,
             *session.posargs,
diff --git a/tests/system/aiplatform/test_e2e_forecasting.py b/tests/system/aiplatform/test_e2e_forecasting.py
index 938d0e27b5..45b16a015f 100644
--- a/tests/system/aiplatform/test_e2e_forecasting.py
+++ b/tests/system/aiplatform/test_e2e_forecasting.py
@@ -18,7 +18,7 @@
 from google.cloud import aiplatform
 from google.cloud.aiplatform import training_jobs
 
-# from google.cloud.aiplatform.compat.types import job_state
+from google.cloud.aiplatform.compat.types import job_state
 from google.cloud.aiplatform.compat.types import pipeline_state
 import pytest
 from tests.system.aiplatform import e2e_base
@@ -103,24 +103,23 @@ def test_end_to_end_forecasting(self, shared_state, training_job):
             )
             resources.append(model)
 
-            # TODO(b/275569167) Uncomment this when the bug is fixed
-            # batch_prediction_job = model.batch_predict(
-            #     job_display_name=self._make_display_name("forecasting-liquor-model"),
-            #     instances_format="bigquery",
-            #     predictions_format="csv",
-            #     machine_type="n1-standard-4",
-            #     bigquery_source=_PREDICTION_DATASET_BQ_PATH,
-            #     gcs_destination_prefix=(
-            #         f'gs://{shared_state["staging_bucket_name"]}/bp_results/'
-            #     ),
-            #     sync=False,
-            # )
-            # resources.append(batch_prediction_job)
+            batch_prediction_job = model.batch_predict(
+                job_display_name=self._make_display_name("forecasting-liquor-model"),
+                instances_format="bigquery",
+                predictions_format="csv",
+                machine_type="n1-standard-4",
+                bigquery_source=_PREDICTION_DATASET_BQ_PATH,
+                gcs_destination_prefix=(
+                    f'gs://{shared_state["staging_bucket_name"]}/bp_results/'
+                ),
+                sync=False,
+            )
+            resources.append(batch_prediction_job)
 
-            # batch_prediction_job.wait()
+            batch_prediction_job.wait()
             model.wait()
             assert job.state == pipeline_state.PipelineState.PIPELINE_STATE_SUCCEEDED
-            # assert batch_prediction_job.state == job_state.JobState.JOB_STATE_SUCCEEDED
+            assert batch_prediction_job.state == job_state.JobState.JOB_STATE_SUCCEEDED
         finally:
             for resource in resources:
                 resource.delete()
diff --git a/tests/system/aiplatform/test_e2e_tabular.py b/tests/system/aiplatform/test_e2e_tabular.py
index daa0364dc5..659a0b6f15 100644
--- a/tests/system/aiplatform/test_e2e_tabular.py
+++ b/tests/system/aiplatform/test_e2e_tabular.py
@@ -189,7 +189,7 @@ def test_end_to_end_tabular(self, shared_state):
 
         # Ensure batch prediction errors output file is empty
         batch_predict_gcs_output_path = (
-            custom_batch_prediction_job.output_info.gcs_output_path
+            custom_batch_prediction_job.output_info.gcs_output_directory
         )
         client = storage.Client()