Hi, I'm
Suryansh
I build scalable backend systems
SCROLL TO EXPLORE
About
Background
I'm a Senior Software Engineer with 5+ years of experience building backend infrastructure and AI-integrated systems — from high-throughput job queues to production RAG pipelines. My recent focus has been Agentic AI: exposing backend logic and live data to LLM agents through clean, well-defined tool interfaces, so agents can reason and act reliably instead of guessing at math or filters.
My core toolkit is Python (FastAPI, Flask), PostgreSQL, and vector search (FAISS, ChromaDB), backed by Docker, GitHub Actions, and AWS for shipping and running things in production. On the agent side, I work with LangChain, LangGraph, CrewAI, and the OpenAI Agents SDK, along with MCP for connecting tools to models. I'm also AWS Certified Solutions Architect.
I care about systems that hold up under real usage — fault-tolerant, observable, built to scale — and I like owning problems end-to-end, from architecture through deployment. Outside of core project work, I enjoy exploring new corners of the AI/agent tooling ecosystem and sharpening the fundamentals — data structures, system design, distributed systems — that hold everything up.
Interests
Agentic AI & MCP
Technical Skills
Languages
Experience
Professional Experience
Senior Software Engineer
GlobalLogic - Hitachi Group
Software Engineer 2
Samsung Research Institute
Software Engineer
Samsung Research Institute
Developer
Standard Chartered Bank
Certifications
Professional Certifications
AWS Certified Solutions Architect – Associate
Amazon Web Services
Projects
SemanticCache
Open-source semantic caching library for LLM calls, using vector similarity search to cut redundant model calls. Decorator-based interface with sync and async support, pluggable embedders (OpenAI, HuggingFace, SentenceTransformers), and pluggable backends (Redis, FAISS, ChromaDB) with configurable similarity thresholds and TTL.
Plug and Play RAG
Developed an open-source, production-ready RAG platform to allow developers to rapidly build and deploy custom Q&A systems. The FastAPI backend, containerized with Docker, supports streaming responses from LLMs like Gemini and connects to enterprise databases (PostgreSQL, MongoDB).
Contact
Get In Touch
I'm always interested in hearing about new projects and opportunities. Whether you have a question or just want to say hi, feel free to reach out!
PHONE
+91 7574922552