Skip to content
View arindam-giri's full-sized avatar
1 follower · 1 following

Block or report arindam-giri

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 supported. This note will be visible to only you.
Report abuse

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

Report abuse
arindam-giri/README.md

Generative AI solution engineer and architect

Experienced GenAI Solution Architect specializing in designing and implementing Generative AI solutions for enterprises using commercial large language models (LLM) and frameworks. Expert at bridging the gap between complex business challenges and advanced GenAI capabilities. Proven track record in multi-agent frameworks, agentic AI platforms, RAG implementations, and legacy system modernization using Generative AI.

Currently pursuing: Claude Code Agent SDK, Microsoft Agent Framework, MCP protocols, Agent to Agent (A2A) protocol, multi-agent collaboration.

Recent enterprise works:

  • Enterprise document analysis: Designed and solutioned a complex Generative AI solution to extract insights for various business quote documents (docx, pdf) by implementing a complex RAG solution. Uses Langchain, Langraph, Python, Claude 3.7, pgvector, difflib, parent document retriever.

  • Legacy System Modernization: Architected and implemented GenAI-powered production solutions for reverse and forward engineering of legacy source code (SAS, Java, Python, VB6, COBOL, TSQL), enabling seamless modernization and scalability. Designed effective solution to handle high volume of lines of code.

  • Multi-Agent Frameworks: Built a multi-agent framework from scratch in Python, leveraging Claude 3.5, with features like orchestration, reasoning, caching, and agentic RAG for faster inference and dynamic learning.

  • Unstructured Data Processing: Designed custom solutions to parse and extract critical information from unstructured data (emails, PDFs, Excel) for post-processing, enabling actionable insights and decision-making.

  • GEN AI/ML Tools & Technologies: Proficient in Claude Sonnet, Claude Opus, Agentic Coding, AWS Lambda, Amazon Bedrock, LangChain and Langraph, with expertise in vector embeddings, few-shot learning, and intelligent agent development.

  • Supported tools for GenAI solutions: NetworkX graph, mermaid diagrams from graph, pdf parsers and creations, Flask, Playwright automation

Personal projects & Open Source contributions

Pinned Loading

  1. core-ML-works core-ML-works Public

    Jupyter Notebook

  2. excel-agent-project-llm excel-agent-project-llm Public

    A complex agentic design and LLM engineering solution to do RAG on complex large excels having tables, unstructured comments, pivots etc without vector. [In progress]

    Python

  3. image-segmentation-test image-segmentation-test Public

    Python