Projects
What I've shipped.
Open-source projects built to understand production systems below the abstraction layer. Each one is a case study, not a demo. Link as attached
- 01
Real-Time Vector Ingestion Engine
ShippedStreaming RAG ingestion pipeline with Kafka backpressure, batched embeddings, provider fallback, idempotent pgvector upserts, DLQ retries, and p95 freshness under 10 seconds.
PythonKafkapgvectorOpenAIPrometheus→ - 02
LLM Evaluation Harness for RAG Regression Testing
ShippedOpen-source CI framework for RAG regression with golden sets, LLM-as-judge scoring, GitHub Actions merge gates, Prometheus drift tracking, and sub-5-second p95 eval runs.
PythonRAGASOpenAIAnthropicGitHub ActionsPrometheus→ - 03
Multi-Agent RAG Orchestration
ShippedA 4-agent retrieval-augmented system on LangGraph with RAGAS evaluation. Faithfulness 73% → 91% over a single-chain baseline.
PythonLangGraphRAGASPostgres + pgvectorPrometheus→ - 04
Distributed Task Queue with Replicated State Store
ShippedFault-tolerant task scheduler built from scratch — 3-node Raft quorum, exactly-once execution under node crashes, lease-based worker locking, and Kubernetes HPA auto-scaling on queue depth.
Java 17Spring BootgRPCKubernetesHPA→ - 05
Distributed Social Media Platform
ShippedA federated social network built from first principles — multi-node Go backend, Raft consensus for leader election, CRDTs for feed merging, and a timeline fan-out system that stays consistent under network partitions.
GoRaftgRPCPostgreSQLRedisDockerKubernetes→
More code on GitHub ↗