DBTB INT Shourabh Rawat
summary
Argues that image recognition can be deployed as an internal service by a small data team using the existing Python web stack, showing an architecture that replaces slow batch handoffs with Django + Celery workers and standard image libraries to deliver a near-real-time prediction engine. Describes how model packaging, async job queues, and a service API cut iteration time, the integration pain points encountered, and practical tradeoffs for ownership, scaling, and monitoring.
AI-written summary · about
related talks
49mdbt: A Software Engineering Approach To The Analytics Workflow
53mData Engineering and AI
23mDelivering Modern Data Stacks With dbt to Operationalise Analytics
46mPath of Data & AI Challenges
46mML Use Cases at Think Big Analytics
05mInterview
39mBuilding Highly Scalable Facial Recognition Pipelines
35mBuilding Data-Intensive Teams