CSE undergrad interested in backend engineering, distributed systems, and AI infrastructure.
I like building things and understanding how they work under the hood. Most of my projects are around backend systems, networking, distributed systems, and LLM infrastructure.
Most of my time goes into building and learning about backend and distributed systems.
I enjoy understanding what’s happening underneath the abstractions networking, concurrency, storage, consensus, queues, and performance. More recently, I’ve also been spending a lot of time with LLM inference, Kubernetes, and AI infrastructure.
I learn best by building things from scratch, which is why most of my projects started as “I wonder how this actually works?” experiments.
RiftMQ — Kafka-inspired queue in Go. Raft consensus, WAL, consistent hashing. 17,900 msg/sec, 100% delivery under 200 producers.
FIX Protocol Trading Gateway — C++20 order engine. Lock-free queues, async I/O. P50: 350µs, P99: 633µs at 250K orders/sec.
LLM Inference Router — OpenAI-compatible gateway across vLLM nodes. Circuit breakers, Prometheus/Grafana observability.
#142 · Namespace filtering for multi-tenant K8s
#161 · InferenceGraph routing for multi-model pipelines