distributed-scheduling

Link Scheduling using Graph Neural Networks, IEEE TWC

Scalable, structured, dynamically-scheduled hyperparameter optimization.

A fault-tolerant distributed job scheduler that delivers priority-based execution, tenant-aware fairness, and resilient checkpointed workloads with leader-elected high availability.

A task scheduler build on top of redis

python redis scheduler

Task scheduling MCP server for autonomous agents — cron, intervals, priority queues, dependencies, retry policies.

This project replaces broken tokenization heuristics for Roman Urdu-English text with a single-feature Ridge model, achieving 2.5× higher accuracy at an ultra-low latency of 0.003 ms. By eliminating subword underestimation, our ML-driven scheduler drops misrouted requests to 3.4%, cutting queue wait times by 28% over standard word heuristics.