Interview Questions

Anonymous Hornet - "label #shape = [batchsize, posids] X #shape = [batch_size, ch] hidden = nn.Linear(batchsize, ch) #shape = [batchsize, ch] logits = nn.Linear(ch, C) #shape = [ch, C] #modifications start here neg_ids = torch.randint(0, C, 0.1 * C) #e.g. if we want to randomly sample only 10% of C outputneg = np.dot(logits[:, negids], hidden(X)) #shape [batch_size, C1] outputpos = np.dot(logits[:, posids], hidden(X)) #shape [batch_size, C2] output = torch.concat(outputpos, outputneg) #concatenate out"See full answer

Ayush kumar S. - "I submitted a PRD as it was a take home assignment."See full answer

Nitish C. - "Delta lake is a metadata layer on top of cloud storage which helps giving datalake transactional capabilities. It helps implement upsert/merge as it conforms a schema to the data assets stored in cloud. It also offers various other capabilities like liquid clustering,time travel, schema evolution,deletes."See full answer

Aneesh D. - "I have worked with tools such as Hadoop, Oracle, DBeaver, and Databricks. I have used these tools at work when dealing with large datasets, data cleaning, data security, and creating models"See full answer

Exponent - "This is a Technical question. It tests your ability to understand high level technical concepts. Even though your job won't have any coding involved, you'll still need to understand these concepts. Being able to cover all these topics with clarity communicates confidence in your interviewer. Unfortunately, there's no formula for technical questions, but some general tips are: Use analogies when you can Break your solution into clear, bite-size steps Don't be afraid to use examples to b"See full answer

Megha S. - "tried my best"See full answer