Skip to content
View surya3586's full-sized avatar
  • South carilona, Spatarnburg

Block or report surya3586

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
surya3586/README.md

Surya Kant Swain — AI Engineer, Full-Stack Python Engineer

I build LLM systems that survive contact with production — evaluation pipelines, RAG, and document intelligence, on top of the microservices and data platforms that feed them. Fifteen years shipping, ten of them in Python.

class Engineer:
    role  = "AI Engineer · Full-Stack Python"
    since = 2011                                    # 15 years of shipping
    focus = ["LLM evaluation", "RAG", "doc intelligence"]

    def philosophy(self) -> str:
        return "If you can't measure the regression, you didn't ship a feature."

What I do

Make LLMs accountable — LangSmith eval harnesses with custom evaluators for accuracy, schema compliance, and latency, benchmarked against public suites and domain sets, because MMLU doesn't know your business.

Ship LLM infrastructure — FastAPI services with OpenAI-compatible schemas over VertexAI and Bedrock. Knowledge Bases, Agents, Guardrails. Every model version replays the eval set before it reaches a user.

Turn documents into data — PDF, DOCX, PPTX, and scans. Azure Document Intelligence + PyMuPDF, layout intact.

Build the boring parts well — Kafka, Databricks, MLflow, Terraform, Kubernetes. The parts nobody demos and everybody pages you about at 2am.

Toolbox

AI / ML
LangGraph LangSmith MLflow PyTorch TensorFlow Bedrock Vertex AI OpenAI MCP

Backend
Python FastAPI Django Flask Node.js GraphQL SQLAlchemy RabbitMQ

Frontend
React TypeScript Next.js Redux Tailwind

Data
Databricks Spark Kafka PostgreSQL SQL Server Pandas NumPy

Cloud / Ops
AWS Azure GCP Docker Kubernetes Terraform Jenkins Prometheus ELK Linux

Currently

Building eval-first LLM systems, poking at MCP and agentic tool-calling, and trying to make both boringly reliable. Happy to argue about chunking strategies, retrieval evals, or whether your agent needs to be an agent — suryaswain612@gmail.com

The debugging technique with the highest hit rate is still: read the error message.

Pinned Loading

  1. multi-agentic-rag multi-agentic-rag Public

    This repository showcases the implementation of a Multi-Agent Research RAG (Retriever-Augmented Generation) Tool built with LangGraph.

    Python 4

  2. LexRAG LexRAG Public

    A Retrieval-Augmented Generation (RAG) application for querying legal documents. It uses PostgreSQL, Elasticsearch, and LLM to provide summaries and suggestions based on user queries. Features data…

    Jupyter Notebook 20

  3. DSA-with-python DSA-with-python Public

    Common data structures (linked lists, stacks, queues, graphs) and algorithms (search, sorting, recursion, dynamic programming) in Python.

    Python 22

  4. machine-learning-pro machine-learning-pro Public

    This repository contains a structured learning path for mastering Machine Learning step by step. It follows a well-defined sequence starting from the basics to advanced ML topics with intuition, ma…

    Python 18

  5. Agent-Foundry Agent-Foundry Public

    Build, publish, and install task-focused AI agents with Claude. No-code studio, shared agent store, streaming generation, and admin moderation. Next.js + PostgreSQL.

    TypeScript 14

  6. aws-bedrock-rag aws-bedrock-rag Public

    Enterprise knowledge assistant using Retrieval-Augmented Generation (RAG) on AWS: fully serverless, built with cost governance and Responsible AI from day one.

    HTML