Projects
Building AI/ML and distributed systems from scratch to understand core concepts deeply.
HybridRAG
AI/MLA cost-optimized enterprise search engine with a three-layer architecture: Ingestion Pipeline for async document processing, Hybrid Retrieval combining semantic and keyword search with reranking, and a Cost Router for intelligent model selection.
Key Features
- Async document ingestion pipeline
- Semantic + keyword search with reranking
- Cost-aware model routing
- Production-ready architecture
K8s Job Scheduler
Distributed SystemsA Go-based HTTP API server for prioritizing and submitting Kubernetes jobs. Features a max-heap priority queue, concurrency control, and graceful shutdown handling.
Key Features
- Priority queue with max-heap implementation
- Kubernetes client-go integration
- Concurrency control mechanisms
- Graceful shutdown handling
Vector Database
AI/MLA complete vector database implementation from scratch in Python. Supports multiple distance metrics (Euclidean, Cosine, Dot Product), CRUD operations, persistence, and semantic search with pre-trained models.
Key Features
- Multiple distance metrics
- Top-k similarity search
- Metadata storage and retrieval
- Semantic search integration
Distributed Systems Mastery
Distributed SystemsA learning repository documenting my journey through distributed systems concepts, implementations, and patterns.
Key Features
- Distributed systems patterns
- Consensus algorithms
- Replication strategies
- Hands-on implementations
Why Build From Scratch?
I believe the best way to truly understand complex systems is to build them yourself. These projects represent my commitment to deep learning — not just using tools, but understanding how they work at a fundamental level. This approach has made me a better engineer and problem solver.