TikTok Interview Questions — Page 10

TikTok·Data Scientist·Technical Phone Screen

May 2026

TikTok data scientist interview that went deep on multicollinearity and feature attribution, specifically what happens when two features are nearly identical and you still need to explain your model. Pretty technical throughout, more stats-heavy than I expected for a DS role.

You have two features A and B with a correlation of 0.98 in a binary classification problem. How would you compute or estimate VIF for each, and what thresholds would you use to flag problematic multicollinearity?
When two features are near-duplicates, how do SHAP values behave differently under interventional versus conditional SHAP, and why can attributions become unstable or split unpredictably between the two?
Walk through a defensible interpretation workflow for a model where two features are near-duplicates. What diagnostics would you run, and what would you expect to see?
What modeling changes would you recommend to handle near-duplicate features, both for a logistic regression and a gradient-boosted tree? How would you validate that you haven't sacrificed predictive performance while improving interpretability?

“VIF I knew cold, regress each feature on the rest and use 1/(1-R^2).”

View Post

TikTok·Software Engineer·Onsite - System Design / Architecture

May 2026

System design round at TikTok for a software engineer role. The whole thing was centered on one big problem: a hotel booking backend that has to survive viral traffic spikes. Felt like a solid interview but there's a lot of ground to cover and I definitely ran out of time on some parts.

Design the backend for a large-scale hotel booking system that needs to handle viral traffic spikes, near real-time availability, and guaranteed no double-bookings.
When would you choose a low-overhead protocol like UDP or persistent WebSocket connections instead of plain HTTP for parts of this system, and which flows can tolerate message loss versus which cannot?
Under high concurrency, how do you prevent two users from both successfully booking the last available room for the same dates?
How would you horizontally partition load for a hotel that suddenly goes viral? Compare sharding by room versus bucketing by user ID.
What data model would you use for hotels, rooms, inventory, and bookings, and how does it support both fast availability lookups and transactional booking writes?

“This is the main question and it sprawls in every direction.”

View Post

TikTok·Software Engineer·Onsite - System Design / Architecture

May 2026

TikTok system design round, one big question that basically ate the whole session. The scope was massive and I kept second-guessing whether to go deeper on one piece or keep moving.

Design a high-traffic service that maintains p99 latency SLOs during sudden traffic spikes. Walk through admission control, token-bucket rate limiting, priority queues, deadlines, and timeouts. Compare different load shedding strategies and explain when to apply each at the load balancer versus the application layer. Also cover circuit breakers, backpressure mechanisms, protecting critical dependencies, and what metrics you'd track to validate everything is working.

“This was basically five questions rolled into one and I felt it.”

View Post

TikTok·Machine Learning Engineer·Technical Phone Screen

May 2026

TikTok ML engineer interview with a classic backtracking problem. Nothing too surprising but the n-queens problem always has more edge cases than you remember until you're actually coding it under pressure.

Given an n x n chessboard, place n queens such that no two queens share the same row, column, or diagonal. Return all valid board configurations, where each is represented as a list of n strings using 'Q' for a queen and '.' for an empty cell.

“I knew immediately it was n-queens but knowing the name and actually coding it cleanly are two different things.”

View Post

TikTok·Data Scientist·Onsite - Behavioral / Leadership

May 2026

Behavioral round for a Data Scientist role at TikTok where the main focus was walking through a past project in depth. Pretty standard format but the follow-up questions pushed harder than I expected.

Pick a project you're proud of and walk me through the business goal, your specific role, the tech stack, obstacles you hit, and the measurable impact. Then tell me what you'd do differently if you were starting it over today.

“This is the kind of question that sounds easy until you're actually in it.”

View Post

TikTok·Product Manager·Onsite - Product Sense / Strategy

May 2026

Interviewed for a PM role at TikTok and got hit with a pretty loaded product ethics question about the algorithm and addiction. Not a lot of context to go on, just the one question that I had to unpack on the spot.

As a Product Manager at TikTok, how would you handle user concerns that the platform's recommendation algorithm is too addictive?

“This one is tricky because you're essentially being asked to critique the core product mechanic that drives TikTok's engagement.”

View Post

TikTok·Software Engineer·Onsite - Product Sense / Strategy

May 2026

One question from a TikTok data science interview, defining success for the platform. Short but surprisingly tricky to answer well.

How would you define success for TikTok?

“Broader than it looks.”

View Post

TikTok·Data Scientist·Technical Phone Screen

May 2026

TikTok data scientist interview with a search relevance scenario focused on brand safety. One meaty product analytics question that required pulling together metrics, diagnostics, and some light system thinking all at once.

Brand clients are complaining that searching their own name on the platform returns irrelevant or harmful results. What metrics would you look at to diagnose this, and how would you approach fixing it?

“My first instinct was to jump straight to precision and recall, which was fine, but I kind of glossed over the brand-safety angle for too long.”

View Post

TikTok·Software Engineer·Technical Phone Screen

May 2026

TikTok software engineering interview that went deep on concurrency, like really deep. They wanted theory, tradeoffs, and a full implementation all in one question, which I was not fully prepared for.

How does multithreading work, and when should you use locks? Compare mutexes, semaphores, and read-write locks including their tradeoffs and when each is appropriate.
How do you identify and prevent race conditions, deadlocks, livelocks, and starvation in concurrent systems?
Design and implement a thread-safe bounded queue that supports multiple producers and multiple consumers using condition variables.
How would you test a concurrent bounded queue for both correctness and performance?

“I started with mutexes because that felt safest and worked my way outward.”

View Post

TikTok·Machine Learning Engineer·Technical Phone Screen

May 2026

TikTok ML engineer interview that went deep on Transformer architecture applied to recommendation systems. The whole session was basically one long design question about cross-attention, which I was not fully expecting.

In a cross-attention block for a recommendation model, how would you define the Query, Key, and Value tensors using a user behavior sequence and a candidate item embedding? What does each tensor represent semantically?
Give at least two different design choices for setting up Q, K, and V in a cross-attention block for user-item recommendation. For each, explain what is attending to what, and the tradeoffs involved.
How does cross-attention differ from self-attention over the user behavior sequence, and why would you use cross-attention specifically in a recommendation setting?

“I fumbled the semantic explanation more than the mechanics.”

View Post