The role was a causal inference-heavy pricing role. Started with an HR phone screen followed by 4 interviews over two rounds.
The first technical round involved foundational causal inference theory questions followed by a pair programming component that involved refactoring ML model code.
The final round consisted of 3 interviews that involved classical ML theory, a case study and behavioural questions respectively.
The entire process took nearly 6 weeks. I was strung along for a few weeks after the final round by HR before I ultimately got a rejection.
Explain how you would perform cross validation on time series data?
In what circumstances would you use ridge regression over lasso and vice versa?
How would you reduce the variance of the average causal effect estimate?
The following metrics were computed from 2 interview experiences for the Expedia Group ML Scientist role in Seattle, Washington.
Expedia Group's interview process for their ML Scientist roles in Seattle, Washington is extremely selective, failing the vast majority of engineers.
Candidates reported having very good feelings for Expedia Group's ML Scientist interview process in Seattle, Washington.