A Deep learning enthusiast with a background in Engineering.
Extensive hands-on experience with Deep Learning, MLOps, Cloud Computing (AWS). Well-versed in NLP, transformers, and distributed training.
Interested in NLP, LLM, Large-Scale Deployment and Inference, Model Optimization, and Kubernetes Ecosystem.
- A Multi-Model, Multi-Modal Agent Based Chatbot on EKS
- End-to-End MLOps Pipeline using SageMaker Pipelines
- RAG - Evaluation via LLM-as-a-Judge and Monitoring
- Multimodal RAG using ImageBind, ChromaDB, and LLaVA
- Deep Learning on HPC/SLURM
- Microservice for deploying Stable (Video) Diffusion
- LLM Inference using RayServe on Kubernetes
- Deploying LLaVA with Constraint-based Sampling on CPU
- Fine-Tuning Model using QLoRa and Deploying via vLLM on KServe
- Deploying Text Generation Model on Kubernetes with Ingress
- Comparison of LLM Quantization
- Canary Deployment via GitOps using Argo CD on EKS
- Multi-Model Deployment with Scaling on EKS via Knative
- CI/CD with Kubeflow Pipelines on EKS with GPU and External Domain
- Kubeflow Pipelines on EKS
- Deploying SDXL on KServe and Monitoring via Prometheus, Grafana, and Kiali
- HPA and Node Scaling using Karpenter on EKS
- RAG with LocalAI + LlamaIndex + ChromaDB
- LLM Evaluation Frameworks