Group Relative Policy Optimization (GRPO) implementations - NanoAhaMoment, GRPO:Zero, Simple GRPO, and GRPO from Scratch - spanning vLLM + DeepSpeed, custom Transformer stack, Bottle HTTP reference server, and pure PyTorch. Compares generation backends, reference policy strategies, reward designs, and loss functions on GSM8K and Countdown tasks.

Production-ready Haystack/LangChain pipelines for Hybrid & Parent-Child Retrieval, Diversity Filtering, MMR, Metadata Filtering, Reranking, Query Enhancement, Multi-Tenancy, Agentic RAG across Pinecone, Weaviate, Milvus, Qdrant, Chroma with dataset loaders, evaluation tooling, and benchmarks for TriviaQA, ARC, PopQA, FactScore and Earnings Calls.

Modular LLM ranking library for Information Retrieval and RAG. Implements state-of-the-art Pairwise, Setwise, and Listwise ranking with structured generation and specialized models (RankZephyr, RankLlama). Features efficient sorting algorithms, sliding windows, and zero-shot capabilities.

Advanced LLM fine-tuning techniques: SFT (LoRA, QLoRA, DoRA, P-/Prefix-Tuning), GRPO, DPO, ORPO, KTO & PPO; composable correctness/format rewards + LLM-as-a-Judge evals (DeepEval, Evidently AI) across math, multi-hop, medical & general QA on Llama 3, Mistral, Phi-4, Gemma & Qwen3. Built on TRL, PEFT & Unsloth.

Training code for advanced RAG techniques - Adaptive-RAG, Corrective RAG, RQ-RAG, Self-RAG, Agentic RAG, and ReZero. Reproduces paper methodologies to fine-tune LLMs via SFT and GRPO for adaptive retrieval, corrective evaluation, query refinement, self-reflection, and agentic search behaviors.

Advanced RAG pipelines for medical (HealthBench, MedCaseReasoning, MetaMedQA, PubMedQA) and financial (FinanceBench, Earnings Calls) QA. LangGraph orchestration + BAML structructed generation, Milvus Hybrid search (Dense + BM25 + RRF), three-layer Metadata Enrichment, Contextual AI instruction-following reranker, and DeepEval evaluation.

Pairwise Ranking Prompting (PRP): Zero-shot LLM reranking library implementing efficient pairwise strategies (Heapsort, Sliding Window, All-Pairs). Mitigates position bias via bidirectional comparison and ensures reliability with structured Pydantic validation. Built for Haystack pipelines.

Medical Reasoning Evaluation

Self-Reflective Question Answering for Biomedical Reasoning. GRPO fine-tuning via QLoRA & Unsloth with rewards for correctness, relevance, groundness, utility & XML structure. Structured think → answer → self-reflection with context grading, relevance assessment & groundness evaluation. DeepEval LLM-as-a-Judge (GEval, Faithfulness, Relevancy).

Advanced RAG pipeline optimization framework using DSPy. Implements modular RAG pipelines with Query-Rewriting, Sub-Query Decomposition, and Hybrid Search via Weaviate. Automates prompt tuning and few-shot selection using GEPA, SIMBA, MIPRO, COPRO, and BootstrapFewShot optimizers on datasets like FreshQA, HotpotQA, TriviaQA, Wikipedia and PubMedQA.