8-stage hybrid retrieval pipeline fusing dense HNSW, BM25 and knowledge-graph traversal with Reciprocal Rank Fusion + cross-encoder reranking. HotpotQA ablation: KG traversal lifted Exact Match 29% → 52%; full pipeline at 66% F1, 80% answer recall, 82% Hit@5, 90% answer-in-context.

End-to-end pipeline: 3,350 instruction-tuning samples across 20 relation types (MinHash dedup, hard negatives, curriculum ordering) + Qwen3-0.6B fine-tune with 4-bit LoRA → 100% schema adherence, 0.6850 composite on multi-axis eval.

Agentic research system based on bisociation. 9-agent LangGraph pipeline with qualifier-driven routing and automated critique loops; persistent workflow state, per-node error boundaries, and a metrics-first evaluation suite.

Recommendation engine for Bureau of Indian Standards (BIS). Most-starred public project with eval script, inference, and presentation. Built with a focus on clean, reproducible evaluation.