Skip to content
View Subhrajyoti8520's full-sized avatar
🎯
Focusing
🎯
Focusing
7 followers · 22 following

Block or report Subhrajyoti8520

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Subhrajyoti8520/README.md

Hi there, I'm SUBHRAJYOTI SOUMYADARSAN 👋

AI Engineer | LLM & Agentic Systems | AI Backend Engineering

Typing SVG

  • 🔭 Currently Engineering:
    • Agentic Systems Engineering • Framework-agnostic runtime engines with dual-mode execution (Dynamic LLM Routing vs. Deterministic State Pipelines)
    • Enterprise RAG & MLOps • Two-stage retrieval architectures, cross-encoder re-ranking, and automated Ragas evaluation.
    • LLM Fine-Tuning & Core DL • Comparative LoRA/QLoRA pipelines (HF PEFT vs. Unsloth) & custom autograd engines
    • High-Throughput Backends • Containerized asynchronous APIs with FastAPI & Docker
  • 💼 Focus Areas: Autonomous Multi-Agent Systems • LLM-as-a-Judge & RAGAS Evaluation(RAGAS) • PEFT (LoRA / QLoRA) • Low-Latency FastAPI Backends • Containerized LLMOps(Docker).
  • 📫 Contact: LinkedIn • Email

🛠️ Languages & Core Technologies

Languages & Backend Infrastructure:
Python FastAPI Docker SQLite Pydantic

AI, Machine Learning & LLM Systems:
PyTorch Hugging Face ChromaDB Unsloth Qdrant Ragas LiteLLM Weights & Biases Streamlit Gradio

Operating Systems & Scripting:
Linux Ubuntu Bash

⚡ Systems Architecture & Technical Competencies

Engineering Pillar Key Implementations & Patterns
Multi-Agent AI Systems Framework-free runtime engines, dynamic LLM routing, deterministic DAG state machines, structured tool calling.
Enterprise RAG & Retrieval Two-stage architectures (Recall + Rerank), Cross-Encoders (BAAI), custom mathematical evaluation sandboxes, vector indexing (ChromaDB, Qdrant).
Evaluation & Quality Benchmarking Ragas framework, automated LLM-as-a-Judge test suites, faithfulness & context precision scoring.
Model Adaptation & PEFT LoRA/QLoRA instruction fine-tuning, Hugging Face PEFT vs. Unsloth Triton acceleration, loss tracking.
AI Backend & Infrastructure Asynchronous REST APIs with FastAPI, Pydantic validation, SQLite/Vector persistence, Docker containerization.

🚀 Highlighted Engineering Projects

Project Focus Area Architectural Highlights
autonomous-multiagent-engine Multi-Agent AI Systems Framework-free runtime engine with dual-mode execution (Dynamic LLM Routing vs. Deterministic State Machines), structured tool dispatch, and integrated RAG.
llm-transpiler Code Gen & Tool Calling Python-to-C++/Rust transpilation engine using AST grammar parsing, LLM tool execution, and benchmarked runtime speedups.
enterprise-rag-evaluation Production RAG & Backend LLMOps A production-grade, two-stage RAG architecture analyzing SEC 10-K financial reports. Pairs a mathematical evaluation sandbox with a custom, framework-free asynchronous REST API, local BAAI cross-encoders, and Docker.
ecommerce-price-cot-finetuning SLM Fine-Tuning & MLOps End-to-end pipeline contrasting direct regression (Llama 3.2) with a Chain-of-Thought engine (Qwen 2.5); features Unsloth Triton acceleration and 4-bit GGUF export for local Docker/Ollama deployment.
pytorch-deep-learning-foundations PyTorch & NN Architecture A production-grade, end-to-end deep learning and computer vision repository covering fundamental tensor mathematics, custom neural architectures, non-linear classification, convolutional vision pipelines (TinyVGG), dynamic data augmentation, device-agnostic GPU acceleration and modular CLI-driven training engines.
deep-learning-cv-foundations Deep Learning Foundations A curated collection of modular, production-focused deep learning implementations and computer vision labs. This repository covers end-to-end workflows: automated data scraping, dataset verification, transfer learning backbones, pixel-level semantic segmentation, categorical tabular embeddings, collaborative filtering, error diagnosis, and standalone model serialization.

Pinned Loading

  1. enterprise-rag-evaluation enterprise-rag-evaluation Public

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

    Jupyter Notebook

  2. ecommerce-price-cot-finetuning ecommerce-price-cot-finetuning Public

    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.

    Jupyter Notebook

  3. llm_fine_tuning_llama_3.2-3b-r1 llm_fine_tuning_llama_3.2-3b-r1 Public

    Fine-tuning Llama-3.2-3B into a reflective reasoning assistant using Unsloth 4-bit QLoRA, SFTTrainer, and ServiceNow R1-Distill data. Quantized to GGUF and served locally via Ollama.

    Jupyter Notebook

  4. deep-learning-cv-foundations deep-learning-cv-foundations Public

    Curated implementations of end-to-end Computer Vision and Deep Learning pipelines: ResNet-18 classification, U-Net semantic segmentation, tabular embeddings, collaborative filtering, and model seri…

    Jupyter Notebook

  5. pytorch-deep-learning-foundations pytorch-deep-learning-foundations Public

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

    Jupyter Notebook