Curated interview practice questions with answers. These are practice scenarios, not a verified list of past interview questions.
About Druva hiring for Data Science roles
Druva is a data protection and backup software company that offers a cloud-native SaaS platform for backup, recovery and data security. It protects data across endpoints, SaaS applications and cloud workloads for enterprises worldwide. The company was founded in Pune, and its large Pune engineering centre hires software engineers, quality engineers, cloud engineers and site reliability engineers.
For Data Science roles, this Druva practice set focuses most on Machine Learning (6), Deep Learning and NLP (6), MLOps and Model Deployment (4), Generative AI and LLMs (4). It has 2 easy, 28 medium, 10 hard questions, so you can start easy and work up to the harder ones.
Company type
Product
Headquarters
California, USA
Main India offices
Pune
Druva Data Science interview process
Online coding assessment
Technical round 1 (DSA)
Technical round 2 (OS, networking or design)
Hiring manager round
HR round
Typical pattern based on public candidate experiences. Rounds vary by role, team and year.
Solved for DruvaStart practicing
3 QUESTIONS FREESign up to unlock the full question bank and track your progress.Unlock every question and answer, then continue practising company-wise and package-wise.
✓ 3 questions free • Unlock the rest in seconds
01
The average delivery time is 30 minutes, yet many customers complain about late orders. How do you investigate?
An average hides the shape of the distribution. Delivery times are usually right-skewed, so a 30-minute mean can include many orders taking 60 minutes or more. Look at the median, the 90th and 95th percentiles and a histogram, then break them down by city, time of day and restaurant. Report the share of orders beyond the promised time, because that is what customers actually experience.
02
Your model performance degrades every few months. Would you retrain on a fixed schedule or based on triggers?
Scheduled retraining, like monthly, is simple and predictable but may be too late after a sudden change or wasteful when nothing changed. Trigger-based retraining runs when monitoring shows drift or a performance drop, which reacts faster but needs reliable monitoring. Many teams combine both: a regular schedule plus triggers for big shifts. Either way, a retrained model must pass the same evaluation gate before replacing the current one.
03
What is a baseline model and why should you build one first?
A baseline is the simplest reasonable prediction, such as predicting the most common class, last week's value or a basic logistic regression. It sets the minimum score any real model must beat. Without it, a 75 percent accuracy can look good when predicting the majority class already gives 80 percent. Baselines also catch pipeline bugs early and show whether extra complexity is worth it.
04
How do you mentor junior data scientists on your team?
Situation: two freshers joined my team and struggled with messy real data. Task: help them deliver independently. Action: I paired with them on the first project, set up weekly code reviews, shared a checklist for validation and leakage, and gave them small end-to-end tasks with clear success metrics. Result: within three months both owned models in production. I focus on teaching how to debug and ask questions, not just giving answers.
05
Your manager asks whether collecting more training data will improve the model. How do you answer using a learning curve?
A learning curve plots training and validation scores against the size of the training set. If both scores are low and close, the model has high bias and needs more features or a more flexible model. If training is high but validation is much lower and the gap narrows as data grows, the model has high variance and more data will help. It tells you whether collecting more data is worth the cost.
06
A customer asks why their loan application was rejected by your model. How do you respond?
I would give a clear, individual explanation, not a technical dump. Using SHAP or reason codes, I would list the top factors, such as high existing EMI burden or short credit history, and say what could improve the outcome. I would also check that the model does not rely on protected attributes or close proxies. For regulated lending, a human review path and documented reason codes are essential.
The ROC curve plots true positive rate against false positive rate across thresholds. AUC is the probability that a random positive is ranked above a random negative; 0.5 is chance.
08
What should you log for a production prediction service?
For each request, log a request ID, timestamp, model version, input features or a hash of them, the prediction and score, and latency. Log errors and fallback use separately. Do not log raw personal data unless needed and allowed; mask it. Aggregate these logs into dashboards for traffic, latency percentiles, error rate and score distribution. Joining logged predictions with later outcomes gives the data for monitoring and retraining.
Start with prompting; it is cheapest and fastest to iterate. Use RAG when the model needs private or frequently changing knowledge, like policy documents, because you can update the index without retraining and cite sources. Use fine-tuning to change behaviour, style or output format consistently, or to make a smaller model handle a narrow task cheaply. Fine-tuning is a poor way to add facts. Many systems combine RAG with a lightly tuned model.
10
How would you fine-tune a pretrained language model for classification?
Add a classification head, freeze or gradually unfreeze layers, use a small learning rate, train on labelled data with validation, and track F1 per class.
11
What is the difference between semantic, instance and panoptic segmentation?
Semantic segmentation gives each pixel a class, such as road or car, but does not separate two cars. Instance segmentation separates individual objects of countable classes, giving each car its own mask. Panoptic segmentation combines both: every pixel gets a class, and countable objects also get an instance ID, while background stuff like sky stays semantic. Autonomous driving and robotics often need panoptic or instance output.
12
Your feature computation on millions of rows uses only one CPU core. Would you use threads or processes to speed it up?
Because of the GIL, threads in CPython do not run Python bytecode in parallel. Threads are fine for I/O-bound work like calling APIs or reading many files. For CPU-bound work like feature computation on chunks, multiprocessing or joblib runs separate processes on separate cores. The cost is process start-up time and copying data between processes. Many NumPy and Pandas operations already release the GIL internally, so measure before adding complexity.
13
Write Python code to compute the Population Stability Index for a feature to detect drift.
Since accuracy cannot be measured quickly, monitor proxies. Track input data drift with PSI per feature, prediction score distribution, the share of transactions flagged, and data quality like missing values. Watch early signals such as chargeback complaints or manual review outcomes on a sample. Set alerts on sudden shifts. When labels arrive, compute real precision and recall by cohort and compare them with the proxy alerts to tune them.
Recursive feature elimination trains a model, ranks features by importance or coefficient size, removes the weakest ones, and repeats until the desired number remains. RFECV picks the number of features using cross-validation. It considers features together rather than one at a time. The downsides are high compute cost on large data and unstable results when features are correlated, so check stability across folds.
16
Write SQL to find the top 3 products by revenue in each category.
WITH rev AS (
SELECT category, product_id, SUM(price * qty) AS revenue
FROM order_items
GROUP BY category, product_id
), ranked AS (
SELECT *, ROW_NUMBER() OVER (PARTITION BY category ORDER BY revenue DESC) AS rn
FROM rev
)
SELECT category, product_id, revenue
FROM ranked
WHERE rn <= 3;
17
Tell me about a time you had to deliver data under an urgent deadline.
Situation: the leadership team needed festive-sale numbers by city for a 9 am review, and the dashboard pipeline had failed overnight. Task: deliver accurate numbers in three hours. Action: I queried the raw orders tables directly, reused validated logic from the dashboard SQL, cross-checked totals with finance's daily figure and flagged two cities with partial data. Result: the review went ahead on time, and I later added pipeline failure alerts.
18
Your credit model has good overall AUC but performs much worse for applicants from one region. What do you do?
First confirm with per-segment metrics and enough samples, since small groups are noisy. Then check why: fewer training examples from that region, different feature distributions, missing data or labels that reflect past biased decisions. Fixes include collecting more data, reweighting, segment-aware features or a separate calibration. Also review fairness and regulatory requirements, and agree with risk and compliance teams on acceptable performance gaps before launch.
19
Your forecast uses actual daily temperature as a feature and looks great in backtesting, but it performs worse in production. Why?
In backtesting you used the actual temperature for future days, which you will never know at forecast time. In production the model gets a weather forecast, which has its own error, so performance drops. This is a subtle form of leakage. Fix the backtest by using the weather forecast that was available on each forecast date, or lagged actuals, so offline results match what production can really achieve.
20
What is a contrastive image-text model like CLIP, and how does it enable zero-shot classification?
CLIP trains an image encoder and a text encoder together on hundreds of millions of image-caption pairs, pulling matching pairs close in a shared embedding space and pushing mismatches apart. For zero-shot classification you embed prompts like 'a photo of a damaged parcel' for each class and pick the class whose text embedding is most similar to the image embedding. It works without task-specific training but may need fine-tuning for niche domains.
21
Your LLM gives different summaries for the same document on different runs, but auditors need consistent output. What do you do?
Set temperature to zero or near zero and fix other sampling settings, and use a seed where the API supports it, though outputs may still vary slightly. Pin the exact model version. Use a structured output format with fixed fields, and reduce ambiguity in the prompt. Cache and store each generated output with its inputs and version, so the stored result, not a regeneration, is what auditors see.
22
How do you pull large data from a SQL database into Pandas efficiently?
Push as much work as possible into SQL: filter, aggregate and select only needed columns before pulling. Use pd.read_sql with a SQLAlchemy engine and chunksize to stream large results. For very large extracts, export to Parquet from the warehouse and read that, which is much faster than row-by-row transfer. Set dtypes like category early, and never use SELECT star on a big table from a notebook.
23
Tell me about a time you stopped a team from shipping a change based on a flawed experiment.
Situation: a team wanted to launch a feature after a test showed a 6 percent lift. Task: as the reviewing data scientist, validate it. Action: I found that assignment was triggered after users clicked into the feature, so treatment had only engaged users. I explained the selection bias simply, proposed assigning at app open, and helped rerun it. Result: the true lift was under 1 percent, and we added assignment checks to the review template.
They store same-type values in contiguous memory and run vectorised operations in compiled C, avoiding Python loop overhead and per-object type checks.
25
How does linear regression work and what are its assumptions?
It fits a line minimising squared error. Assumes linearity, independent errors, constant variance (homoscedasticity), normally distributed residuals and no strong multicollinearity.
Evaluate retrieval and generation separately. For retrieval, build a set of real questions with known relevant documents and measure recall at k and mean reciprocal rank. For generation, measure faithfulness to retrieved context, answer correctness and relevance, using human review on a sample and an LLM-as-judge with a clear rubric at scale. Track latency and cost too. Rerun the same evaluation set after every change to prompts, chunking or models.
28
Which activation functions do you know and when to use them?
ReLU for hidden layers, sigmoid for binary outputs, softmax for multi-class outputs and tanh when zero-centred outputs help; Leaky ReLU avoids dead neurons.
29
How do one-stage and two-stage object detectors differ?
Two-stage detectors, like Faster R-CNN, first propose candidate regions and then classify and refine each one, which gives strong accuracy, especially for small objects, but is slower. One-stage detectors, like YOLO and SSD, predict boxes and classes directly over a dense grid in a single pass, making them fast enough for real-time video. Modern one-stage models have closed most of the accuracy gap, so they dominate edge and video use cases.
30
How would you build RFM features for a customer churn model?
RFM stands for recency, frequency and monetary value. From the transactions table, for each customer as of a cut-off date: recency is days since the last purchase, frequency is the number of orders in the last 90 days, and monetary is total or average spend in that window. Compute them using only data before the cut-off, add trends like spend this month versus last, and the label from the period after.
31
Most of your products sell zero units on most days, with occasional sales. Which forecasting approach suits this?
This is intermittent demand, and standard models like ARIMA forecast a small constant that is useless for stocking. Croston's method and its SBA variant forecast the size of non-zero demand and the interval between sales separately. Alternatives are aggregating to weekly level, or using a global gradient boosting model with Tweedie or Poisson loss. Evaluate with MAE or MASE, not MAPE, because zero actuals break percentage errors.
Gradients shrink as they pass through many layers (for example with sigmoid), so early layers barely learn. ReLU, residual connections and good initialisation help.
33
Your detector finds large objects well but misses small objects like distant people. How do you improve it?
Small objects lose detail after downsampling. Train and infer at higher input resolution, or tile large images into overlapping crops. Use a backbone with a feature pyramid so detection happens on high-resolution maps. Tune anchors or assignment settings for small sizes, and oversample images with small objects. Check labelling quality for tiny boxes too. Measure mAP on small objects separately to confirm improvement.
34
Pandas: find the top 3 products by revenue in each region.
Three weeks is too little to learn seasonality, so borrow information. Find similar past launches by category, price band and channel, and use their early sales curves as analogues. A global model trained across many products, with product attributes as features, can also forecast a cold-start item. Combine this with planned marketing spend and business judgement, show a wide interval, and update the forecast weekly as real data arrives.
Quantisation stores model weights in lower precision, such as 8-bit or 4-bit integers instead of 16-bit floats. A 7-billion parameter model drops from about 14 GB to around 4 GB at 4-bit, so it fits on smaller GPUs or even laptops and runs faster. The cost is some loss in quality, usually small at 8-bit and noticeable on hard tasks at very low bits. Common formats include GPTQ, AWQ and GGUF.
The probability of seeing a result at least as extreme as the observed one if the null hypothesis were true. A small p-value is evidence against the null, not proof that the alternative is true.
38
Write Pandas code to read a large CSV in chunks and compute total sales per city.
# process 1 million rows at a time
import pandas as pd
totals = {}
for chunk in pd.read_csv('sales.csv', usecols=['city', 'amount'], chunksize=1_000_000):
part = chunk.groupby('city')['amount'].sum()
for city, amt in part.items():
totals[city] = totals.get(city, 0) + amt
result = pd.Series(totals).sort_values(ascending=False)
39
Your test shows a 2 percent lift in conversion, but revenue per user went down. What do you do?
Do not ship on conversion alone. Check whether the change shifted buyers to cheaper items, increased discount usage or pulled in low-value orders. Break down revenue into conversion times average order value, look at item mix, and confirm the revenue drop is statistically meaningful rather than noise. Then go back to the agreed primary metric and guardrails; if revenue is the business goal, it should guide the decision.
40
Your neural network's training loss suddenly becomes NaN. What do you check?
Common causes are a learning rate that is too high, exploding gradients, bad input values, and unstable maths like log of zero. I would check the input data for NaN or infinite values, lower the learning rate, add gradient clipping, and make sure the loss uses the stable built-in version with logits. With mixed precision, I would check the loss scaler. Logging gradient norms per step helps find the exact point it breaks.
Tips to crack the Druva Data Science interview
Revise operating systems, file systems and networking basics, since backup and storage products rely heavily on these concepts.
Practise DSA problems in your main language and be ready to discuss how you would design a scalable backup service.
Learn basic cloud services such as object storage and compute on AWS to connect your skills with Druva's platform.
Keep a one-minute story ready for every project on your CV: problem, your part, tools, result.
Practise the hard questions on this page aloud; Druva interviewers usually ask follow-ups on your first answer.
Frequently asked questions
How many rounds are there in the Druva Data Science interview?
Candidates usually go through 5 stages: Online coding assessment; Technical round 1 (DSA); Technical round 2 (OS, networking or design); Hiring manager round; HR round. The exact rounds change with the role, team, location and your experience, so confirm the process with the recruiter.
Which topics should I prepare for the Druva Data Science interview?
This practice set leans on Machine Learning (6), Deep Learning and NLP (6), MLOps and Model Deployment (4), Generative AI and LLMs (4). Revise those first, then practise explaining one or two of your own projects end to end, because most Druva interviewers ask you to walk through real work.
Are these the exact questions asked at Druva?
No. These are curated practice questions that match the skills and difficulty usually tested in product interviews like Druva's. They are not a leaked or verified list of past questions.
Where does Druva hire Data Science professionals in India?
Druva has large teams in Pune. Openings and locations change often, so check the Druva careers page and filter by city and experience.