Real-time computer vision and GenAI / RAG systems: low-latency GPU inference pipelines and the scalable FastAPI microservices that serve them in production.
- Vision · detection and tracking pipelines, GPU inference, ONNX / TensorRT export
- GenAI · retrieval pipelines, vector search, local and hosted LLM serving
- Backend · FastAPI services, queues and caching, containerised deploys
Reach me at pradeepmurugesan.dev@gmail.com.
Vision & ML
GenAI
Backend & Data
Infra
|
|
|
|
|
|
|
|
|
|
Credly verified |
Azure AI: plan and prepare to develop AI solutions |
Microsoft Foundry: select, deploy, evaluate models |
Open to collaboration and roles in applied AI. · Back to top



