diff --git a/charts/model-engine/templates/gateway_deployment.yaml b/charts/model-engine/templates/gateway_deployment.yaml
index 726d6e85..fe726ee1 100644
--- a/charts/model-engine/templates/gateway_deployment.yaml
+++ b/charts/model-engine/templates/gateway_deployment.yaml
@@ -60,6 +60,7 @@ spec:
               path: /readyz
               port: 5000
             periodSeconds: 2
+            timeoutSeconds: {{ ((.Values.gateway).readinessProbeTimeoutSeconds | default 5) }}
             failureThreshold: 30
           command: 
             - dumb-init
diff --git a/charts/model-engine/values.yaml b/charts/model-engine/values.yaml
index 15ba6bf9..15ce1eeb 100644
--- a/charts/model-engine/values.yaml
+++ b/charts/model-engine/values.yaml
@@ -33,6 +33,12 @@ celery_broker_type_redis: null
 #     drop:
 #       - ALL
 
+# gateway [optional] tuning for the gateway deployment.
+gateway:
+  # readinessProbeTimeoutSeconds sets the /readyz probe timeout. The k8s default of 1s
+  # ejects saturated-but-healthy pods and concentrates load on the survivors.
+  readinessProbeTimeoutSeconds: 5
+
 redis:
   auth:
   authSecretName: ""
diff --git a/model-engine/model_engine_server/api/app.py b/model-engine/model_engine_server/api/app.py
index 534aebb5..4c77e1de 100644
--- a/model-engine/model_engine_server/api/app.py
+++ b/model-engine/model_engine_server/api/app.py
@@ -313,8 +313,13 @@ def load_redis():
     get_or_create_aioredis_pool()
 
 
-def healthcheck() -> Response:
-    """Returns 200 if the app is healthy."""
+async def healthcheck() -> Response:
+    """Returns 200 if the app is healthy.
+
+    Must be async: a sync handler runs in the shared threadpool, so under load the
+    probe queues behind blocked requests and misses its timeout, ejecting pods that
+    are saturated but healthy.
+    """
     return Response(status_code=200)