Subhrajyoti Soumyadarsan

An AI-powered transpiler that converts Python code into highly optimized C++ or Rust. Features a Gradio web UI, AST-based security checks, and real-time performance benchmarking.

PyTorch deep learning workflow covering tensor math, non-linear classification, TinyVGG vision pipelines, dynamic augmentations, and modular CLI training engines.

A production-style, two-stage Financial RAG architecture analyzing SEC 10-K reports. Features an evaluation sandbox (RAGAS) and an asynchronous, containerized FastAPI backend powered by Gemini Flash and ChromaDB.

Fault-tolerant autonomous market-arbitrage engine featuring a tripartite consensus system (PyTorch DNN, Ollama GGUF, ChromaDB RAG reranking), dual deterministic/ReAct execution, a 3D vector-space telemetry dashboard and user alerts.

No project description available.

A comparative fine-tuning and MLOps pipeline for e-commerce price prediction, taking Llama-3.2 and Qwen-2.5 from raw training text to quantized 4-bit local Docker/Ollama deployment.