Available question text
Scope:
- User interaction with this service
- Sharding of Data
- Resource Allocation
- How does orchestration work
- How does User know the status
- How do we handle script failures
- How does progress aware retry-ability happen
Related questions
Continue with questions that share topics or the same question type.
- Design a batch inference API
ML system design · API Design · ML System Design · System Design Fundamentals
- Design a high-concurrency LLM inference service
ML system design · LLM Inference & Serving
- Design a Low-Latency GPU Inference Service
ML system design · LLM Inference & Serving · ML System Design · System Design Fundamentals
- Improve an ML Inference Service
ML system design · ML System Design
Sources · 1 reference
These records explain where the question appears. A company tag or candidate report does not guarantee a future interview question.
Hello Interview · 1 record
DoorDash
Design an Offline Batch Inference Service
Reported Jul 11, 2025 · 1 source report
SENIOR
Source snapshot: Nov 12, 2026
View source