Applied Scientist Interview Questions

Showing 61–75 of 75 results

• MicrosoftMedium·Applied Scientist
  Maximum Subarray Sum of an Array Repeated K Times

  A coding question that first asks for the largest sum of a non-empty contiguous subarray, then for the same quantity when the array is written out k times back to back. It tests subarray reasoning across copy boundaries, all-negative inputs, and sums that overflow 32-bit integers.

  Coding & AlgorithmsOnsite
• MicrosoftMedium·Applied Scientist
  Predict Employee Attrition from an HR Dataset and Explain Its Drivers

  A machine learning design exercise: given a tab-separated HR dataset with features such as age, job role, monthly income and overtime, predict which employees will leave and explain which factors drive attrition. It covers feature processing, model choice, class imbalance, evaluation metrics, threshold selection and interpretability.

  ML System DesignOnsite
• NVIDIAMedium·Applied Scientist
  How AI Agents Fit Into Your Research Workflow: Ideas, Experiments, and Paper Writing

  A research internship interview question about how AI agents change a researcher's daily workflow across generating ideas, running experiments, and writing papers. It tests concrete delegation choices, how agent output is verified, awareness of failure modes such as fabricated references, and judgment about confidentiality and reproducibility.

  Behavioral & LeadershipTechnical Screen
• NVIDIAMedium·Applied Scientist
  Research Project Deep Dive and Your AI-Agent Research Workflow

  Present a 20-minute deep dive into one research project covering motivation, research question, training pipeline, results and takeaways, then extend it to the internship problem. The round also asks how AI agents fit into your daily research workflow for writing, experiments and ideation, testing technical depth, honesty about results, and verification habits.

  Behavioral & LeadershipOnsite
• OpenAIMedium·Applied Scientist
  Extensible card-hand ranking: three of a kind, flush, pair and a discard rule

  A three-part object-oriented coding exercise built around a card game: rank hands by three of a kind, pair and high card, insert a flush category, then add a discard rule that removes hands that are not a pair, returning a log of each game. It tests extensible design, deterministic tie-breaking and absorbing rule changes cleanly.

  Software Engineering FundamentalsOnsite
• WayfairMedium·Applied Scientist
  Evaluate Post-Purchase Recommendation Emails

  Evaluate post-purchase recommendation emails through incremental profit, useful timing, customer eligibility, randomized holdouts, and unsubscribe or complaint guardrails.

  Product / Decision MakingOnsite
• WayfairMedium·Applied Scientist
  Rank Homepage Modules for an E-Commerce Product

  Rank e-commerce homepage modules using business objectives, seasonal eligibility, slot effects, slate diversity, cold-start exploration, and page-level experiments.

  ML System DesignOnsite
• WayfairMedium·Applied Scientist
  Set Bids for Search Advertising from Business Value

  Design search-ad bidding from expected business value, with budget pacing, delayed conversion feedback, auction assumptions, and incremental-profit evaluation.

  ML System DesignTechnical Screen
• WayfairMedium·Applied Scientist
  Simulate and Compare Multi-Armed Bandit Strategies

  Compare epsilon-greedy, UCB1, and Thompson sampling in a reproducible Bernoulli bandit simulation with reward, pseudo-regret, and repeated-run uncertainty.

  Machine LearningOnsite
• EeBayEasy·Applied Scientist
  Behavioral: beyond-scope ownership, manager conflict, and a skip-level deadline at risk

  A behavioral question set on taking on work beyond your scope, handling a disagreement with your manager when discussion fails, and responding when a task from your skip-level manager will miss its deadline. It tests ownership, managing up, escalation judgment and communicating risk early.

  Behavioral & LeadershipTechnical Screen
• EeBayEasy·Applied Scientist
  Behavioral: choosing a large cross-time-zone company, role fit, and on-call motivation

  A behavioral question set for a machine learning role on why you want a large company with cross-time-zone teams rather than a small one, why this position, and how you stay motivated when the role carries heavy on-call duty. It tests genuine motivation, self-awareness and ownership of production systems.

  Behavioral & LeadershipTechnical Screen
• EeBayEasy·Applied Scientist
  Design fast query-to-listing retrieval over tens of millions of listings

  An ML system design question on retrieving relevant listings for free-text search queries across a catalog of tens of millions of items with low latency. It tests candidate generation, indexing, embedding training, freshness, filtering and scaling, plus the offline and A/B test metrics used to evaluate retrieval.

  ML System DesignTechnical Screen
• EeBayEasy·Applied Scientist
  Docker optimization, container fundamentals, and CI/CD for an ML model service

  Practice explaining how Docker images, layers, build caching and container isolation work, then optimizing the image and runtime of a Python ML inference service. The question also covers continuous integration, delivery and deployment for shipping a containerized model safely.

  Software Engineering FundamentalsTechnical Screen
• EeBayEasy·Applied Scientist
  Named entity recognition: framing, algorithm choice, data processing, and metrics

  A machine learning question on named entity recognition for short e-commerce text such as listing titles and search queries. It asks you to define the task, compare NER algorithm families and choose one, plan labeling and data processing, and select entity-level and product-level metrics.

  Machine LearningTechnical Screen
• EeBayEasy·Applied Scientist
  Optimizing BERT inference latency and throughput for a production NLP service

  An ML engineering question on speeding up a fine-tuned BERT encoder that has become too slow or too costly to serve in production. It tests profiling, model compression, runtime and serving optimizations such as batching and padding control, and how to verify that accuracy does not regress.

  Machine LearningTechnical Screen