NVIDIA Senior staff coding interview questions
These are the 3 coding questions YourAlly has tagged for NVIDIA at Senior staff. On the YourAlly ladder this is Senior staff, the same level as Google L7, Meta E7 and Amazon L8.
A coding round at a large tech company usually runs 45 to 60 minutes with one or two problems. You write code that runs, test it on your own examples and state its time and space cost. At this level coding is often a smaller part of the loop, but the bar for clarity and speed stays high.
Practice a mock NVIDIA Senior staff coding loopPractice NVIDIA coding questions
Dynamic Batcher Completion TimesFree to read
Simulate an inference server's dynamic batcher. Requests arrive in time order and queue FIFO. A batch is sent to the earliest free model instance once the queue holds max_batch requests or the oldest request has waited max_delay. A batch of k requests takes base_cost + per_item_cost * k. Return each request's completion time.
Input: arrivals = [0,1,2,3], max_batch = 2, max_delay = 10, base_cost = 5, per_item_cost = 1, instances = 1 Output: [8,8,15,15]
What a strong answer covers
- Trigger as min of the delay deadline and the fill time
- Dispatch at the later of trigger and earliest free instance
- Batch limited to arrived requests and max_batch
- Min-heap of instance free times
- Argument that FIFO order and monotone dispatch times hold
2 more coding questions
- Buddy Allocator for Device Memory Locked
- Pipeline Stages Under a Memory Cap Locked
Related pages
More NVIDIA Senior staff rounds
- Behavioral 4 questions
NVIDIA coding at other levels
Other companies at this level
- Adobe Senior staff 4 questions
- Airbnb Senior staff 4 questions
- Amazon L8 6 questions
- Anthropic Senior staff 5 questions
- Apple Senior staff 7 questions
- Cisco Senior staff 3 questions