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

  1. 01

    Real-Time Vector Ingestion Engine

    Shipped

    Streaming RAG ingestion pipeline with Kafka backpressure, batched embeddings, provider fallback, idempotent pgvector upserts, DLQ retries, and p95 freshness under 10 seconds.

    PythonKafkapgvectorOpenAIPrometheus
    →
  2. 02

    LLM Evaluation Harness for RAG Regression Testing

    Shipped

    Open-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
    →
  3. 03

    Multi-Agent RAG Orchestration

    Shipped

    A 4-agent retrieval-augmented system on LangGraph with RAGAS evaluation. Faithfulness 73% → 91% over a single-chain baseline.

    PythonLangGraphRAGASPostgres + pgvectorPrometheus
    →
  4. 04

    Distributed Task Queue with Replicated State Store

    Shipped

    Fault-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
    →
  5. 05

    Distributed Social Media Platform

    Shipped

    A 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 ↗