Backend / Distributed Systems / Applied ML
Building reliable backend systems with fault tolerance, replication, recovery, and pragmatic ML applications.
I build backend systems with a focus on reliability, performance, and maintainability. I’m interested in service design, data flow, and how systems evolve as complexity grows.
I enjoy working across APIs, scaling, and failure handling, and thinking through practical tradeoffs. I also explore how machine learning can be applied to problems with real constraints, where practicality matters more than theory.
Distributed IRC-style chat system with gossip-based replication, fault-tolerant client/server recovery, and load-aware routing via replicated Addressing Servers, built on an event-driven Java NIO architecture for scalable non-blocking concurrency.
Studied whether occlusion-aware training improves indoor cat/dog detection under partial visibility using synthetic ADE20K indoor-object occlusions and a real occluded test set; evaluated YOLOv8, EfficientDet-D0, and DETR with COCO-style mAP.
Reusable genetic algorithm framework for hyperparameter tuning across scikit-learn models using tournament selection, crossover/mutation, elitism, and constraint-aware handling of invalid configurations.
Python scheduling system for city-wide soccer games/practices under dense constraints and weighted preferences using a hybrid Genetic Algorithm + AND/OR-tree search that minimizes penalty to reach feasible, high-quality schedules.