PMLE Scaling Prototypes into ML Models — Timed 30 Questions

Question 1

You are deploying a deep learning model on edge devices with limited computational resources. The model must run inference in <10 ms and the model size must be under 50 MB. Currently, your trained model is 200 MB and runs in 50 ms. Which combination of model compression techniques should you apply?

30 minute time limit — choose an answer to begin.

Accepted Answer

Apply post-training quantization (INT8) and pruning. Post-training quantization (INT8) reduces model size ~4x and speeds inference by using 8-bit integers instead of 32-bit floats, while pruning removes redundant weights to further shrink the model and reduce compute. Together they can bring a 200 MB / 50 ms model under 50 MB and under 10 ms with minimal accuracy loss, making them the most practical combination for edge deployment. Quantization-aware training and knowledge distillation are heavier lifts that may not be necessary to hit these targets.

Answer

Only apply weight pruning

Answer

Apply quantization-aware training and knowledge distillation

Answer

Use knowledge distillation to train a smaller student model

Question 2

You are running a Vertex AI custom training job with pre-built TensorFlow container. You want to use TPU v3 pods for faster training. Which configuration is required?

Accepted Answer

Specify machine type as tpu-v3-8 in the worker pool spec and use tf.distribute.TPUStrategy. To use TPU v3 pods in a Vertex AI custom training job with a pre-built TensorFlow container, you specify the TPU machine type (e.g., tpu-v3-8) in the worker pool spec and use tf.distribute.TPUStrategy in your training code. The pre-built container already includes the TPU libraries, so no custom container is needed, and the distribution strategy is required for the code to address the TPU cores correctly.

Answer

Set the worker pool machine type to n1-standard-8 and add --accelerator type=tpu

Answer

Use a custom container with TPU libraries and set --tpu-topology=v3-8

Answer

Enable TPU by setting the environment variable TPU_NAME

Question 3

You are fine-tuning a large language model using Vertex AI Training with spot VMs to reduce cost. Your training job keeps getting preempted, causing delays. Which THREE strategies can help mitigate the impact of preemption?

Accepted Answer

Enable checkpointing and restore from the latest checkpoint after preemption. Option A is correct because periodic checkpointing to Cloud Storage lets the job resume from the last saved state after a spot VM is preempted, so no training progress is lost and the restart cost is bounded. Option B is correct because adding worker replicas (distributed data-parallel training) increases throughput, so the job completes more work per unit of wall-clock time and is more likely to finish before the next preemption event. Option E is correct because a smaller, more efficient architecture requires fewer compute cycles and less memory, shortening total training time and thus reducing exposure to preemption windows. Option C is not right because reducing batch size mainly lowers memory pressure and can even slow convergence, which does not directly mitigate preemption impact. Option D is not right because switching to dedicated, non-preemptible VMs eliminates preemption entirely rather than mitigating its impact, and it forfeits the cost savings that motivated using spot VMs.

Answer

Reduce batch size to lower memory usage

Answer

Switch to dedicated (non-preemptible) VMs

Question 4

You are building a machine learning pipeline on Google Cloud. You need to perform feature engineering on large datasets stored in BigQuery and store the resulting features in Vertex AI Feature Store for both online and offline use. Which TWO Google Cloud services should you use?

Accepted Answer

Dataflow. Dataflow can read from BigQuery, compute features via Apache Beam, and write to Feature Store. Alternatively, Dataproc can also do this but Dataflow is more serverless. Cloud Functions is not suitable for large-scale. Cloud Build is for CI/CD. BigQuery ML is for in-database ML.

Answer

Cloud Functions

Answer

BigQuery ML

Answer

Cloud Build

Question 5

A data scientist wants to train a TensorFlow model on Vertex AI using a pre-built container. Which of the following pre-built containers is NOT available for custom training in Vertex AI?

Accepted Answer

Apache Spark. Vertex AI provides pre-built containers for TensorFlow, PyTorch, scikit-learn, and XGBoost. There is no pre-built container for Apache Spark in the Vertex AI training service; Spark jobs are typically run on Dataproc.

Answer

TensorFlow

Answer

PyTorch

Answer

scikit-learn

Question 6

You are performing hyperparameter tuning on Vertex AI with Vizier. You want to maximize the accuracy of your model, and you have a budget of 50 trials. Which algorithm should you choose to best explore the search space?

Accepted Answer

Bayesian optimization. Vertex AI Vizier's default and recommended algorithm for hyperparameter tuning is Bayesian optimization, which builds a probabilistic surrogate model of the objective function and uses an acquisition function to pick the next trial most likely to improve accuracy. With a 50-trial budget, Bayesian optimization converges faster than random or grid search by exploiting information from prior trials. This makes it the best choice for maximizing accuracy within a fixed budget.

Answer

No algorithm; use default Vertex AI tuning

Answer

Grid search

Answer

Random search

Question 7

You are fine-tuning a pre-trained BERT model from Hugging Face for a sentiment analysis task using Vertex AI training. The dataset has 100k examples. To avoid catastrophic forgetting, which layer freezing strategy should you apply?

Accepted Answer

Unfreeze all layers and fine-tune the entire model. The option marked [CORRECT] is A because full fine-tuning of all layers is the standard and most effective approach for adapting a pre-trained BERT model to a downstream sentiment analysis task with a sufficiently large dataset (100k examples). Catastrophic forgetting is primarily a concern when the target dataset is small or when the new task is very different from the pre-training objective; with 100k examples, the model has enough signal to adjust all weights without losing general language understanding. Freezing layers would unnecessarily restrict the model's capacity and typically lead to lower accuracy. Thus, unfreezing all layers and fine-tuning the entire model is the recommended strategy.

Answer

Freeze the first 6 layers, fine-tune the last 6 layers

Answer

Freeze all layers except the classification head

Answer

Use transfer learning only on the embeddings layer

Question 8

Which Vertex AI service allows you to discover, fine-tune, and deploy foundation models with a few clicks, including models like Llama and Gemma?

Accepted Answer

Vertex AI JumpStart. Vertex AI JumpStart is the service within Vertex AI Model Garden that provides a curated collection of foundation models (including Llama, Gemma, and others) with one-click deployment, fine-tuning, and notebook samples. It simplifies the process of discovering and using open-source and third-party models. Model Garden is the broader catalog, but JumpStart is the specific feature for quick deployment and fine-tuning.

Answer

Vertex AI Prediction

Answer

Vertex AI Vizier

Answer

Vertex AI Model Garden

Question 9

You want to deploy a trained scikit-learn model to Vertex AI for online predictions. The model file is 2 GB. Which option should you use?

Accepted Answer

Use a custom container with the scikit-learn model. The correct option is B: use a custom container with the scikit-learn model. Vertex AI's pre-built scikit-learn containers have a model size limit (typically around 500 MB for the default serving container), so a 2 GB model file exceeds what the pre-built container can handle, and a custom container lets you package the model and any custom inference code without that constraint. Option D fails for the same size reason, since the pre-built scikit-learn container cannot accommodate a 2 GB artifact. Option A is not a real Vertex AI deployment mechanism (there is no 'large model VM' option for this purpose), and Option C is unsuitable because Cloud Functions has deployment package and memory limits far below 2 GB and is not designed for hosting ML models for online prediction.

Answer

Use AI Platform (now Vertex AI) with a large model VM

Answer

Use Cloud Functions to host the model

Answer

Upload the model to Vertex AI Model Registry and deploy using pre-built scikit-learn container

Question 10

You need to reduce the cost of training a large model on Vertex AI while maintaining fault tolerance. Which THREE actions should you take? (Choose 3)

Accepted Answer

Use spot VMs. Option A (Use spot VMs) is correct because spot (preemptible) VMs on Vertex AI cost significantly less than standard VMs, and fault tolerance is preserved when combined with checkpointing so training can resume after preemption. Option D (Enable checkpointing and save to Cloud Storage) is correct because periodic checkpoints written to durable Cloud Storage (GCS) allow the job to restart from the last saved state after a spot VM is preempted, which is the mechanism that makes cheap preemptible capacity safe to use. Option E (Use a single worker with multiple GPUs instead of multiple workers) is correct because consolidating onto one worker with multiple GPUs avoids the inter-worker communication overhead and synchronization complexity of distributed multi-worker training, reducing cost and failure surface while still using multiple accelerators. Option B (MultiWorkerMirroredStrategy) is not appropriate here because it is a distributed training strategy that increases coordination overhead and fault-tolerance complexity rather than reducing cost. Option C (Use TPUs instead of GPUs) is not a guaranteed cost-reduction action for this scenario, since TPU pricing and availability vary and switching hardware does not by itself provide fault tolerance.

Answer

Use MultiWorkerMirroredStrategy

Answer

Use TPUs instead of GPUs

Question 11

You are fine-tuning a Gemma model using Vertex AI JumpStart. You want to combine the fine-tuned model with a custom output layer for a unique task. Which TWO components are required to deploy the combined model? (Choose 2)

Accepted Answer

Vertex AI Model Registry. Option C (Vertex AI Model Registry) is required because the fine-tuned Gemma model combined with the custom output layer must be registered as a model resource in Vertex AI Model Registry before it can be deployed to a Vertex AI Endpoint; the registry provides versioning and serves as the source artifact for deployment. Option D (Custom container with the model and custom head) is required because a custom output layer/head is not part of the standard Gemma serving image, so you must package the fine-tuned model weights together with the custom head into a custom container that implements the Vertex AI prediction server contract (e.g., serving HTTP on the required port with predict/health routes) so the combined model can serve inference. Option A (Vertex AI Feature Store) is not needed because feature storage/online serving of features is unrelated to deploying a fine-tuned model with a custom head. Option B (Cloud Run) is not needed because Vertex AI model deployment uses Vertex AI Endpoints, not Cloud Run, for hosting the model. Option E (Pre-built container for Gemma) is not suitable because a pre-built Gemma container cannot include your custom output layer, so it cannot serve the combined model.

Answer

Vertex AI Feature Store

Answer

Cloud Run

Answer

Pre-built container for Gemma

Question 12

A machine learning engineer is preparing to train a Transformer-based model using TensorFlow on a single TPU v3-8 pod slice. The training script uses tf.distribute.TPUStrategy. Which environment variable must be set in Vertex AI to enable TPU training with the appropriate topology?

Accepted Answer

TPU_CONFIG. Vertex AI automatically sets the TPU_CONFIG environment variable to communicate the TPU worker IP address and port to the training container. TF_CONFIG is used for distributed training with CPUs/GPUs, but TPU_CONFIG is the correct one for TPU training.

Answer

TPU_NAME

Answer

XRT_TPU_CONFIG

Answer

TF_CONFIG

Question 13

A team wants to perform hyperparameter tuning on a Vertex AI custom training job with 100 trials. They require an algorithm that efficiently explores the search space by learning from previous trials. Which algorithm should they select in the study configuration?

Accepted Answer

ALGORITHM_UNSPECIFIED (defaults to Bayesian optimization). In Vertex AI hyperparameter tuning, if you do not specify an algorithm, the default is Bayesian optimization, which efficiently explores the search space by learning from previous trials. The option ALGORITHM_UNSPECIFIED explicitly defaults to Bayesian optimization, making it the correct choice for an algorithm that learns from prior trials.

Answer

RANDOM_SEARCH

Answer

HYPERBAND

Answer

GRID_SEARCH

Question 14

A company wants to bring their own Docker container to Vertex AI for training a model with a custom framework. They need to ensure the container is compatible with the Vertex AI training service. What is the minimum requirement for the container?

Accepted Answer

The container must include a Python script that reads command-line arguments and outputs a trained model to /tmp/model. Vertex AI custom container training expects the container to run a training script that reads command-line arguments (e.g., hyperparameters and data paths) and outputs the trained model. An HTTP server on port 8080 is not required; the training service launches the container and passes arguments via command-line. Health checks are handled internally by Vertex AI, not by the container itself.

Answer

The container must be based on a Google-provided base image

Answer

The container must expose an HTTP server on port 8080 that responds to health checks and starts the training job when called

Answer

The container must expose an HTTP server on port 8080 and handle /health and /predict endpoints

Question 15

A data scientist wants to quickly experiment with a pre-trained Vision Transformer model from Hugging Face and fine-tune it on a custom dataset using Vertex AI. They want to use a managed environment with minimal setup. Which Vertex AI service should they use?

Accepted Answer

Vertex AI JumpStart. Vertex AI JumpStart is the correct choice because it provides a managed environment with pre-built, optimized containers for popular models like Vision Transformers, enabling one-click deployment and fine-tuning with minimal setup. It abstracts away infrastructure management, allowing the data scientist to quickly experiment without configuring custom training scripts or environments.

Answer

Vertex AI Prediction

Answer

Vertex AI Workbench

Answer

AI Platform Training

Question 16

A company is deploying a deep learning model on edge devices with limited storage and computational resources. They need to reduce the model size by 80% while maintaining acceptable accuracy. Which two techniques should they combine?

Accepted Answer

Quantization and pruning. Quantization reduces model size by converting weights from FP32 to INT8, achieving up to 75% size reduction. Pruning removes redundant weights (e.g., 50% pruning) to further shrink the model. Together, these two techniques can reduce model size by over 80% (e.g., 50% pruning + INT8 quantization yields ~87.5% reduction) while preserving acceptable accuracy on edge devices. Knowledge distillation also reduces size but typically requires a pre-trained teacher and may not achieve the extreme compression needed when combined with quantization alone.

Answer

Pruning and distillation

Answer

Quantization and distillation

Question 17

A company is fine-tuning a large language model (Gemma 7B) using Vertex AI JumpStart. They want to reduce the model's memory footprint for deployment on edge devices. Which THREE model compression techniques should they consider?

Accepted Answer

Post-training quantization to INT8. Post-training quantization to INT8 (A) is correct because it converts the model's FP32/FP16 weights to 8-bit integers after training, cutting memory usage roughly 2-4x with minimal accuracy loss, which is ideal for edge deployment. Quantization-aware training (C) is correct because it simulates quantization during fine-tuning so the Gemma 7B model learns to compensate for reduced precision, yielding better accuracy than post-training quantization alone at the same low-bit footprint. Pruning of weights with small magnitude (E) is correct because removing near-zero weights reduces parameter count and model size, directly lowering the memory footprint on edge devices. Using a larger batch size during inference (B) is incorrect because batch size affects throughput and activation memory, not the model's stored weight footprint, and larger batches actually increase memory use. Increasing the number of layers (D) is incorrect because adding layers enlarges the model and increases memory requirements, the opposite of compression.

Answer

Using a larger batch size during inference

Answer

Increasing the number of layers

Question 18

Your team is deploying a large language model (LLM) on Vertex AI for online prediction. The model exceeds the maximum request size for Vertex AI Prediction. Which approach should you take to serve this model?

Accepted Answer

Deploy the model on a Compute Engine VM with a custom container and a load balancer. Vertex AI online prediction enforces a maximum request size (1.5 MB for HTTP, 10 MB for gRPC) that cannot be raised by changing machine type or protocol. When the model's input payload exceeds this limit, the correct workaround is to move off the managed prediction service and host the model yourself on a Compute Engine VM with a custom container behind a load balancer, where you control request size limits.

Answer

Use Vertex AI Endpoint with a larger machine type and gRPC

Answer

Use Vertex AI Batch Prediction

Answer

Split the model into smaller parts and deploy multiple endpoints

Question 19

An ML engineer wants to use Vertex AI Model Garden to deploy a pre-trained foundation model for text summarisation. What is the quickest way to achieve this?

Accepted Answer

Use Vertex AI JumpStart to deploy the model with one click. Vertex AI JumpStart provides a streamlined way to deploy pre-trained foundation models from Model Garden with just a few clicks, often with one-click deployment options. It abstracts away the complexity of containerization, endpoint configuration, and scaling, making it the quickest method for deploying a pre-trained model for text summarization.

Answer

Use Vertex AI AutoML for text summarisation

Answer

Use Vertex AI Pipelines to build a custom training pipeline

Answer

Export the model from Model Garden and deploy using a custom container

Question 20

You are performing post-training quantisation of a trained TensorFlow model to INT8 for deployment on edge devices. Which technique should you use to minimise accuracy loss?

Accepted Answer

Quantisation-aware training. Quantisation-aware training (QAT) simulates the effects of quantisation during training by inserting fake quantisation nodes, allowing the model to learn weights that are robust to the reduced precision. This minimises accuracy loss compared to post-training quantisation methods.

Answer

Float16 quantisation

Answer

Post-training integer quantisation with calibration

Answer

Post-training dynamic range quantisation