I build high-performance backend systems, AI-powered applications, and modern full-stack platforms with a strong focus on:
- β‘ Scalable architecture
- π§ Generative AI systems
- π¬ Media streaming infrastructure
- π₯οΈ GPU-first local AI workflows
- π₯ Developer experience & framework engineering
Currently focused on building production-grade systems using:
FastAPI β’ Python β’ Next.js β’ TypeScript β’ PostgreSQL β’ Docker
AI/ML β’ Diffusion Models β’ RTX 5090 β’ Kubernetes β’ AWSDesigning scalable systems for:
- HLS media streaming
- Real-time interaction layers
- AI-generated video pipelines
- Diffusion/video model workflows
- High-throughput GPU inference systems
Deep diving into:
- Diffusion model pipelines
- SDXL ecosystem
- Video generation systems
- Local LLM infrastructure
- Fine-tuning workflows
- Multi-GPU optimization
- RTX 5090 AI workstation engineering
Diffusers β’ SDXL β’ ControlNet β’ LoRA β’ Local LLMs
PyTorch β’ GPU Optimization β’ AI Video PipelinesSystem Design
Distributed Systems
Streaming Infrastructure
Generative AI
GPU Systems
Realtime Architecture
Modern Web Frameworks
AI-assisted Development
High Performance APIsπ« Email: aniketsarkar@yahoo.com
βBuild systems that scale. Build tools that matter. Build AI locally.β