Skip to content
View SID-SURANGE's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report SID-SURANGE

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.

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
sid-surange/README.md

Siddharth Surange · AI Engineer

Building production-grade AI systems — from RAG pipelines and agentic workflows to local LLM tooling. I work at the intersection of Generative AI, NLP, and MLOps, with a focus on shipping things that actually run.


About Me

  • Day job: AI Engineer, building LLM-powered products in production
  • Current interests: Agentic architectures, RAG with real retrieval quality (deduplication, ranking, citations), and local LLM setups with quantized models
  • How I work: I prefer running things locally first — LM Studio, quantized Llama/Granite models — before scaling to cloud APIs
  • Community: I write on Medium about things I wish were better documented, and I deploy experiments to Hugging Face Spaces

🛠️ Tech Stack

Category Tools
Languages Python
LLM Orchestration LangChain LangSmith OpenRouter
Models & Embeddings Hugging Face PyTorch OpenAI
Backend & Data FastAPI PostgreSQL Qdrant
Cloud & Infra Google Cloud Platform Vertex AI Docker Railway
UI Gradio

🌟 Featured Projects

Briefcast

Briefcast

Automated AI research briefing agent — monitors Google AI, DeepMind, OpenAI, Anthropic, arXiv and more, then delivers a curated daily digest to Telegram with follow-up Q&A over a 14-day rolling knowledge base.

Stack: FastAPI · PostgreSQL + pgvector · LangChain LCEL · OpenRouter (Gemini, Claude) · APScheduler · Railway

Highlights: dual-layer deduplication (SHA-256 + cosine similarity), tiered source ranking, RAG answers with citations, ~$8/month to run in production

Resume Parser

ResumeParser

HR-focused resume analysis tool that runs entirely on local LLMs — no API keys required. Extracts structured data from PDFs, flags missing sections, generates tailored interview questions, and visualizes resume content.

Stack: FastAPI · Gradio · PyTorch · IBM Docling · LM Studio (quantized Llama 3.1/3.2, IBM Granite)

Highlights: fully offline, 8-bit quantized model support, spell-check analysis, word cloud generation

AI Sandbox

PageSense · AgentForge · AI-Sandbox

Monorepo of production-grade experiments. PageSense: Chrome extension + FastAPI/Qdrant backend for semantic search over your browsing history. AgentForge: deployed agentic app with web search and image generation.

Stack: FastAPI · Qdrant · Gradio · smolagents · LlamaIndex · JavaScript (extension)


✍️ Writing


🏆 Certifications

  • Oracle Certified Generative AI Professional
  • Google Cloud Professional Data Engineer

📫 Connect

LinkedIn Hugging Face Medium

Pinned Loading

  1. ResumeParser ResumeParser Public

    A FastAPI and Gradio-powered application that extracts structured information from PDF resumes. Streamlines resume screening with automated parsing, analysis, and visualization features, making HR …

    Python 1

  2. ai-sandbox ai-sandbox Public

    A personal AI sandbox for learning, experimenting, and prototyping different AI use cases and techniques.

    Python

  3. State-Farm-Distracted-Driver-Detection State-Farm-Distracted-Driver-Detection Public archive

    Springboard Capstone - State Farm Distracted driver detection

    Jupyter Notebook 2 1

  4. briefcast briefcast Public

    Personal AI intelligence briefing agent — ingests Google AI, Anthropic, OpenAI, and the broader AI ecosystem, ranks and summarises updates, and delivers a daily briefing to Telegram with RAG query-…

    Python