vinayak = {
"role" : "AI Research Associate @ Vidur Research",
"education" : "B.Tech CSE @ KIIT University (2023–2027)",
"location" : "India 🇮🇳",
"focus" : ["Production RAG Systems", "LLM Fine-tuning", "Agentic Workflows"],
"currently" : "Building financial intelligence systems with CRAG + RAGAS at scale",
"philosophy" : "Real products > notebooks. Metrics > vibes.",
}
- 🔭 Building CRAG pipelines that cut hallucinations 30% across 50+ financial instruments
- ⚡ Achieved 95%+ temporal accuracy with evidence gating + contradiction detection
- 🤖 Fine-tuned Phi-2 (2.7B params) with LoRA — 85% command accuracy, 40% faster inference
- 📊 Integrated RAGAS evaluation driving 10–20% retrieval gains per iteration
- 🏆 First Prize — FED Hackathon (NLP-integrated finance tracker)
- 📰 Shipped The Vector Daily — automated AI newsletter processing 100+ articles/day
| 🏢 |
AI Research Associate · Vidur Research (Subsidiary of Dreamskrin)
|
| 🔬 Project | 💡 What it does | 📈 Results |
|---|---|---|
| 🧩 PrepGraph | RAG chatbot — hybrid BM25 + FAISS, semantic cache, smart query router (Llama 8b/70b) | ↓40% LLM calls, ↓25% latency, ↓30% inference cost |
| 🖥️ Command Copilot | NL → Linux commands · LoRA fine-tuned Phi-2 · offline FastAPI deployment | 85% accuracy, ↓40% inference time, zero cloud dependency |
| 👗 Reel2Retail | Fashion video → product detection + vibe classification (YOLOv8 + CLIP + NLP) | End-to-end CV + NLP pipeline |
| 📊 HIVE Big Data | MovieLens analytics on Hadoop / HDFS / HiveQL (Cloudera stack) | Distributed analytics on 25M+ ratings |
