An MLOps workflow for training, inference, experiment tracking, model registry, and deployment.

A comprehensive .NET MAUI plugin for ML inference with ONNX Runtime, CoreML, and platform-native acceleration support

gRPC server for Machine Learning (ML) Model Inference in Rust.

[TPDS 2025] EdgeAIBus: AI-driven Joint Container Management and Model Selection Framework for Heterogeneous Edge Computing

ML service for cats that actually learn stuff. PPO brains, personality drift, mood system. Built in 10hrs

PoC demonstrating distributed workload orchestration using Ray as the primary compute framework with Prefect for workflow orchestration, supporting cloud-native deployments (Kubernetes)

Production-ready ML model serving with FastAPI, TensorFlow, Docker, Kubernetes, and Prometheus. Features CI/CD, health checks, and scalable inference.

Submission of Project

Enterprise Data Warehouse & ML Platform - High-performance platform processing 24B records with <60s latency and 100K records/sec throughput, featuring 32 fact tables, 128 dimensions, and automated ML pipelines achieving 91.2% accuracy. Real-time ML inference serving 300K+ predictions/hour with ensemble models.

A lightweight, framework-agnostic middleware that dynamically batches inference requests in real time to maximize GPU/TPU utilization.

Client-side React + Vite web app to record and process voice audio and send features to an API for automated stress prediction (speech-based stress detection).

Kickstart your MLOps initiative with a flexible, robust, and productive Python package.

Microservice to digitalize a chess scoresheet

scripts for benchmarking vLLM using Llama 8b and NVIDIA 4090 GPU